Author SHA1 Message Date
xslandCursor 45bda80859 feat: 接口1/6 标注层字号上调一档 + 眉心改用 9 号点定位
- annotation: 自适应字号系数 0.017→0.020(下限 8→9),标注文字更大更清晰
- measure: _brow_center 只取 FaceMesh 9 号点(眉间上点),不再与 151 取中点

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-30 22:58:49 +08:00
xslandCursor b78da0e0cd feat: 脸型分类器(7分类)+批量报告生成
基于 MediaPipe 468 关键点提取几何特征,转 z 分数后与各脸型原型加权匹配。
参考分布与原型靶心取自 1093 张测试集的实测画像,不再靠人工设定绝对阈值。

方形脸占比从 29.6% 降到 13.8%,两处原因:一是参考统计量原先只由 50 张样本
估得,相对全量人群有系统性偏移,且三项偏移都在给方形脸加分;二是原型把
aspect_ratio 当作方形脸的主特征,但实测方脸组该值中位仅 +0.16,真正"宽"的
是圆脸(+1.01),等于在拿脸宽找方脸。

原型参数在「6 张基准标注图判定不变、且领先第二名 >=3 分」的约束下搜索得到。
余量约束是必要的:早前一版余量仅 0.008 分,权重写码时四舍五入就会翻转结论。

测试素材(人像照片)与报告输出体积大,一并加入 .gitignore。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-29 11:37:09 +08:00
xsl 616fc26143 fix: 删除 MeasureResult.__init__ 中重复的七眼厘米赋值块 2026-07-27 23:16:59 +08:00
xsl 48c9875381 feat: 接口1/5/6 发际线弃用逻辑(顶庭<0.7cm)+接口1调试页分步可视化
- measure.py: MeasureResult 增 hairline_discarded 判定(顶庭<0.7cm),弃用时
  顶/上庭字段置null、face_total只算中下庭、hairline_source=discarded
- annotation.py: 弃用时保留头顶线、去掉发际线、只标中/下庭
- app.py: 接口1/6 弃用分支 + eye1/7竖向范围改用眉心 + 接口1调试页(measure-debug)
- 新增 static/test_interface1_debug.html 分步可视化页(9步原理)
2026-07-27 23:07:54 +08:00
xsl 5bcaeb2594 chore: 所有提示词统一为"填充遮罩区域的头发"
测试结论: 纯生发提示词(不做皮肤处理)效果最佳。
- 替换所有位置的提示词默认值(原"填充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜"等)
- 涉及25个文件: app.py/hairline/service.py/hairline/redraw.py/工作流json/测试页/benchmark脚本/local_test
- _REDRAW_PROMPT / _DEFAULT_PROMPT / 各接口Form默认值 / 测试页输入框默认值 全部统一
2026-07-26 21:53:39 +08:00
xsl 8a82d00056 docs: 所有报告最左边新增原图(输入图)列
- bench3/4/5/7 报告重新生成,首列显示输入原图
- 补充 girl2 原图到 static/bench/orig/
- regen_reports.py: 通用报告重生成脚本
2026-07-26 21:44:31 +08:00
xsl e2bbcca7ad docs: 重绘分辨率对比(纯生发提示词) bench7报告
提示词="填充遮罩区域的头发"(纯生发,无皮肤处理)
80/80成功,0 OOM,峰值21.2GB
对照 bench3(美颜)/bench4(磨皮)/bench5(美白)/bench7(纯生发)
2026-07-26 21:41:43 +08:00
xsl f8ed477696 docs: 重绘分辨率对比(美白提示词) bench5报告
提示词="填充遮罩区域的头发,皮肤加一点美白"
80/80成功,0 OOM,峰值21.2GB
可对照 bench3(美颜)/bench4(磨皮)/bench5(美白) 三种提示词
2026-07-26 21:00:49 +08:00
xsl 2877d07a69 docs: 重绘分辨率对比(无美颜提示词) + 调试接口支持自定义提示词
- app.py/hairline/service.py: 调试接口新增 redraw_prompt 参数,_call_local_redraw 支持自定义提示词
- benchmark_res_prompt.py: 提示词改为"填充遮罩区域的头发,皮肤加一点磨皮"(去掉美颜)
- static/bench4_report.html: 20行×4分辨率对比报告,80/80成功,0 OOM

可对照 bench3(含美颜) vs bench4(无美颜) 看画质差异
2026-07-26 19:57:36 +08:00
xsl bee7a487ac docs: 重绘分辨率对比报告(原图/896/768/640)
4图×5发型=20行,每行4分辨率对比,steps=15,热数据。
80/80成功,0 OOM,峰值21.2GB(原图不缩放也未OOM)。
报告: static/bench3_report.html
2026-07-26 19:10:33 +08:00
xsl 531dcb8279 docs: swap步数+重绘分辨率对比报告(热数据)
4图×2发型×(3步数档+3分辨率档) 热数据对比,48/48成功,0 OOM,峰值20.6GB。
- benchmark_steps_res.py: 测试脚本(预热+正式取热数据)
- benchmark_steps_res_report.py: 报告生成
- static/bench2_report.html: 对比报告
- static/bench2/: 48张结果图

结论: B维度 steps10→20 swap 3.0s→3.9s; C维度 res640比896省3s(comfy 4.3s vs 7.3s)
2026-07-26 17:44:59 +08:00
xsl 62d2660e41 feat(调试): 测试页新增重绘分辨率选项
- app.py 调试接口新增 redraw_max_side 参数,控制整条管线的降分辨率
- debug_grow_timing.html 新增"重绘分辨率"下拉(640/768/896/1024/原图)
- 实测: 640比896省1.5s(5.2s vs 6.7s), 1024比896慢0.6s
2026-07-26 17:01:27 +08:00
xsl e4d03a782d feat(调试): swapHair webui步数暴露到测试页可调
参数透传链路: 测试页→debug接口→generate_hairline_redraw→_grow_core
  →_call_swap→change_hair swapHair→webui_img2img→build_body_v2

- app.py: 调试接口新增 webui_steps Form 参数
- hairline_grow.py: _call_swap/_grow_core/generate_hairline_grow/generate_hairline_redraw 透传 webui_steps
- debug_grow_timing.html: 新增 swap步数 下拉(默认/10/15/20/25/30)

实测 steps 10→25 swap 耗时 4.1s→4.4s,参数确实生效
2026-07-26 16:49:21 +08:00
xsl ae5a3b8f1d refactor(comfyui): 模型切换时同步VAE + 完善编码器映射
- 新增 _vae_for_unet() 按模型自动切换 VAE(Z-Image用ae, Flux.2用flux2-vae)
- _clip_for_unet 增加 z-image 识别
- 为将来多模型切换做准备(当前 Q4 不受影响)
2026-07-26 16:12:43 +08:00
xsl d318efcff0 feat(调试): 接口2女性生发分步耗时分析页面
新增 /api/v1/debug/grow-timing 调试接口 + debug_grow_timing.html 测试页:
- 拆分接口2女性生发的每一步并独立计时(extract_context/mask/swap/blend/comfyui)
- 测试页用条形图展示各步耗时占比,附步骤说明
- 用于定位性能瓶颈,优化方向判断

实测花瓣发型: 总11.9s = 预处理0.44s + 换发型4.4s + ComfyUI重绘6.8s
2026-07-26 16:12:32 +08:00
xsl ff4019c570 chore: 默认模型固定为 9B-Q4_K_M,测试页移除模型/分辨率选择器
测试结论: 9B-Q4_K_M 分辨率896 为最佳性价比组合。
- 三个工作流(0716add-hair-api/add_hair/hair_repaint)默认模型改为
  flux-2-klein-9b-Q4_K_M.gguf (UnetLoaderGGUF节点)
- test_interface2.html 移除 Flux模型/压图长边 下拉选择器,
  接口调用不再传 flux_model/redraw_max_side,统一用工作流默认(Q4/896)
2026-07-25 16:25:44 +08:00
xsl 5226e23989 save code 2026-07-25 16:22:41 +08:00
xsl c462fd3634 refactor(报告): 图片改为独立JPG文件引用,不再base64内嵌
- 测试结果图(258张)和原图(3张)以JPG存入 static/bench/{matrix,hairstyle,orig}/
- 报告HTML改为 <img src> 引用相对路径,体积从 ~45MB 降至 ~30KB
- 报告和图片均部署在 static/ 下,可通过URL直接访问
2026-07-25 16:20:28 +08:00
xsl ab6b0cb0bb docs: 添加模型对比/发型对比 HTML 测试报告
报告图片已压缩为内嵌 JPG(缩放至300px宽,质量70),体积从 ~45MB 降至 ~3MB:
- static/benchmark_report.html: 4模型×3分辨率矩阵对比 (2.7MB)
- static/hairstyle_report.html: 3图×5发型×10组合对比 (3.1MB)

同步更新报告生成脚本支持图片压缩,并从 .gitignore 移除报告文件排除。
2026-07-25 16:17:14 +08:00
xsl 94cdfd6de5 feat(接口2): 支持动态切换Flux模型+分辨率 + 模型对比测试脚本
代码改动:
- comfyui.py: run() 新增 unet_name 参数,提交前自动改写模型节点
  (.gguf→UnetLoaderGGUF, .safetensors→UNETLoader),并按模型自动同步
  文本编码器(4b→qwen_3_4b, 9b→qwen_3_8b),避免切换时维度不匹配
- redraw.py: run_redraw() 透传 unet_name
- service.py: generate_grow_results_swap/generate_grow_results 支持
  redraw_max_side(分辨率参数化) 和 unet_name 透传
- app.py: 接口2 新增 flux_model/redraw_max_side 两个 Form 参数(男女路径都加)
- test_interface2.html: 新增 Flux模型/压图长边 下拉选择器
- add_hair.json/0716add-hair-api.json: 工作流默认模型改为 9b

测试脚本:
- benchmark_matrix.py: 4模型×3分辨率×3图×3次 矩阵测试
- benchmark_hairstyle.py: 3图×5发型×10组合 发型对比测试
- benchmark_report.py/benchmark_hairstyle_report.py: HTML报告生成

清理:
- .gitignore: 排除 benchmark_out/、报告HTML、gateway.log、*.bak.*
- 移除 gateway.log 的 git 跟踪
2026-07-25 16:16:13 +08:00
xsl f509fe99b4 docs: 同步 integration.html / 接口文档.md / test_interface5.html
- 接口5: 补 generate_grow_image 参数说明(接口文档/integration/test_interface5 加控件)
- 接口1/5/6: 补 left_position/right_position 字段(MediaPipe 21/251号点)
- 接口4: features 字段纠正为固定6个英文字段(原误写~42项含中文, 与代码不符)
- 接口7: 完全移除(代码已 deprecated=True 固定返回错误, 文档却当正常接口详述)
- 错误码: 删错误的'1004已废弃'(1004仍用于接口2/5 gender校验), 补 1004 正确描述 + 1009(X-Internal-Token鉴权)
- test_interface5.html: 加 generate_grow_image 复选框
2026-07-24 00:42:34 +08:00
xsl a1d458eb20 feat(接口1/5/6): 返回数据新增 left_position/right_position(MediaPipe 21/251号点)
- face_mesh_landmarks.py: 加常量 LEFT_POSITION=21 / RIGHT_POSITION=251
- measure.py: MeasureResult 收 landmarks/宽高, to_response 顶层输出两点(原图像素 {x,y}, 与 landmarks 同格式)
- measure_face 透传 landmarks(签名不变, 6处调用零改动); __init__ 用 None 默认值守卫向后兼容
- 三接口自动生效: 接口1/6 在 data 顶层, 接口5 在 face_measure 对象里(复用同一 to_response)
- 实测坐标左右镜像合理, 44 个现有测试全过无回归
2026-07-24 00:42:26 +08:00
xsl 92e628b0d5 feat(接口5): 新增 generate_grow_image 参数控制是否生成生发效果图
- app.py: 接口5 路由加表单参数 generate_grow_image(bool, 默认 True)并透传
- hairline/service.py: generate_hairline_pngs 加同名参数, False 时跳过 ComfyUI 生发、grown_png 恒 None
- 默认行为不变(向后兼容); false 时仅返回三档发际线叠图与中心点, 大幅降低耗时
- 网关字节级透传 multipart, 新参数自动到达 worker, 无需改网关
2026-07-24 00:42:18 +08:00
xslandCursor b4714cedf3 perf(接口2女): REDRAW_MAX_SIDE 默认 1024→896 兜底
1024 档下部分大图(swapHair ~5.3s 地板 + ComfyUI 重绘)仍会踩 12s 线。
压到 896 后 ComfyUI 段稳定 ~4s,女性路径总耗时 9~11s,留出安全余量。
追画质可用环境变量 REDRAW_MAX_SIDE=1024 覆盖;接口2男/接口3 的
GROW_B_MAX_SIDE 保持 1024 不变(单段 ComfyUI,无 swapHair 地板)。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-23 01:42:27 +08:00
xslandCursor e7b62f2b2e perf(接口2): 稳定混跑耗时至12s内 —— ComfyUI插队 + CLIP挪CPU + 提示词全局统一
问题:接口2 与接口3/5 乱序调用时耗时抖动(最差 15~22s)。两个根因:
1. GPU 24G 常驻 21.4G,Flux-2(3.9G) 无法完全驻留显存,每次采样动态换页,
   速度随空闲显存波动(2s~8s);
2. ComfyUI 单队列 FIFO,接口2 排在接口3/5 批量任务后面。

改动:
- hairline/comfyui.py: run() 新增 front 参数,/prompt 带 "front": true 插队到队列最前;
  redraw.py 透传;service.py 接口2 三处调用(女重绘 + 男有/无遮罩)传 front=True,
  接口3/5 仍走普通队列。
- add_hair.json / 0716add-hair-api.json: 节点61 CLIPLoader device default→cpu。
  qwen CLIP(4G) 不再占显存(文本条件缓存常年命中),ComfyUI 显存 8.8G→4.5G,
  Flux-2 完全驻留,采样稳定 ~3-5s。代价:换 prompt 后首次请求 CPU 编码 ~11s(一次性)。
- 提示词全局统一为「填充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜」:
  app.py 4处默认值、service.py _REDRAW_PROMPT、redraw.py _DEFAULT_PROMPT、
  4个工作流节点60内置文案、测试页(test_interface2/3/7/12/12_final)、local_test。
  任何两个不同 prompt 交替提交都会打爆 CLIP 编码缓存(--cache-classic 只存最近一次),
  之前测试页旧文案与服务端不一致导致交替测试每次 +11s。
- app.py: 接口7 /api/v1/hair/grow-v2 下线(业务弃用;add_hair2.json 的 Klein-9b
  会把常驻 Klein-4b 挤出显存)。保留 stub 返回 1007 明确报错,避免裸 404。

实测(1024 档):接口2女 8.5~10s、接口2男 ~5s、接口3 ~7-10s,交替混跑无尖刺。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-23 01:01:48 +08:00
xslandCursor 4291f125d4 fix(接口2): 发际线钳制到头部轮廓,修复短发/光头照片发际线贴到头部外面
短发/剃光头照片(如男性椭圆发际线)中间锚点射线检测命中不到 hair 像素时,
sample_hairline 的 fallback 会用固定 0.18 归一化偏移把点顶到头部轮廓外的背景,
在有效/失效锚点交界处形成尖角,被贴图不透明像素蒙到后露出戳出头部的线条。

新增 clamp_hairline_to_silhouette + sample_hairline_clamped,在几何检测后按每列
SegFormer(skin∪hair) 轮廓上沿做安全网钳制;extract_context 固定改用钳制版本。
只在 fallback 越界时生效,正常长发照片结果与旧行为一致,纯 numpy/opencv 与 GPU 无关。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-22 23:41:52 +08:00
xslandCursor 7fc0210ce6 fix(pose): 修正正面照被误判为1003(solvePnP翻转解)
ITERATIVE 偶发收敛到相机后方(tz<0),roll≈±180° 超阈值,
把正面照误判为非正面。检测到负深度时回退 SQPNP 重解正深度解。
补充回归测试。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-21 16:47:04 +08:00
xslandCursor 085ad3ced0 接口1 四庭七眼标注:字体更小、数值带cm、增加百分比、线名右移居中对齐
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-19 23:37:59 +08:00
xslandCursor 2993a0b948 perf(接口2/3): 混合调用零模型换出且响应<12s
- 三接口统一 ComfyUI 重绘 prompt「填充遮罩区域的头发,皮肤加一点磨皮」,
  避免 CLIP 文本条件缓存失效导致的反复重载(单卡装不下 Flux+CLIP 同驻)。
- 接口2 女重绘整条管线(swapHair+ComfyUI)送模型前限边 REDRAW_MAX_SIDE(默认1024),
  overlay 预览保持全分辨率,结果放大回原尺寸。
- 接口2 男/接口3 单段推理经 _prep_comfy_input 限边 GROW_B_MAX_SIDE(默认1024)。
- 修复真实大图(1257x1495)全分辨率送模型导致 13~21s 且把 Flux 挤出显存的问题。
- comfyui.py 增加输入尺寸日志;service.py 增加女重绘分段计时(swap/blend/ComfyUI)。

实测真实图三接口任意交替: 女9~12s / 男7.8s / 接口3 6.6s,CLIP/Flux 重载 0 次。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-19 20:08:21 +08:00
xslandCursor 08b31a3baa fix: 测试页同时兼容 base64 与 URL 图片字段
直连 worker 返回 *_base64、经网关则改写为 *_url;统一 resolveImgSrc 后接口1/2/3/5/6 测试页都能正确显示结果图。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-19 15:49:46 +08:00
xsl 51e313e845 save code 2026-07-19 00:51:46 +08:00
xsl fbbcd48418 feat: 系统配置文件适配 RTX 3090
更新系统服务配置文件:
- hair-worker.service: 路径从 /home/xsl/ 改为 /home/ubuntu/,添加 comfyui/change_hair 依赖
- comfyui.service: 添加 --cache-classic --fast 标志优化性能
2026-07-18 19:18:52 +08:00
xsl 74ccab0ff8 feat: 适配 RTX 3090 (24GB) 环境优化
硬件迁移:从 RTX 5090 (32GB) 迁移到 RTX 3090 (24GB)

主要改动:
1. hairline/comfyui.py: 轮询间隔从 0.2s 降到 0.05s
2. hairline/service.py: PNG 编码 compress_level=1,节省 ~240ms
3. add_hair.json: 工作流使用 4B FP8 模型 + steps=4
4. static/test_interface3.html: 修复图片显示(添加 data:image/jpeg;base64, 前缀)

性能优化后接口3响应时间:6.6-7.3s(之前 8.66s)
2026-07-18 18:58:40 +08:00
xslandCursor 659c037270 feat: ComfyUI 改走 10.60.74.221,测试页上传图超阈值自动降采样
将 worker 默认 ComfyUI 地址改为远端 10.60.74.221:8188;前端测试页在像素超过 1536000 时等比缩小到 786432 以内。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-17 02:23:35 +08:00
xsl c1bb9614c7 save code 2026-07-17 01:54:04 +08:00
xsl 2b1f528ddd perf: 接口2/12 跳过 viz 叠图生成,省 ~80ms
compute_mask 新增 render_viz 开关(默认 True 保持接口11 行为不变)。
接口2/12 路径(generate_hairline_redraw)传 render_viz=False,跳过 6+ 张
overlay JPG 的 _jpg_b64 编码(baseline/upper/hair_seg/mask/hairline/pushed),
只保留必需的数据字段(_inner_pts/_outer_pts/_upper_mask/mask_pixels)。
2026-07-17 01:37:53 +08:00
xsl d9e96aca87 chore: 重绘服务改走内网 10.60.74.221:8899
gpu_worker 与重绘服务在同一内网,走内网地址(3ms 延迟,比公网更稳定)。
三处调用地址(service.py / test_interface12 / test_interface12_final)
由公网 117.50.183.232 改为内网 10.60.74.221。仍可用 HAIR_LOCAL_REDRAW_URL 覆盖。
2026-07-17 00:57:58 +08:00
xsl 8aed389d79 chore: 重绘服务拆到远程机器 117.50.183.232:8899
接口2 female 后端(generate_grow_results_swap)、test_interface12.html、
test_interface12_final.html 三处重绘调用地址由本机 127.0.0.1:8899 改为远程
117.50.183.232:8899,本机不再跑重绘服务(释放本机显存)。

地址仍可用 HAIR_LOCAL_REDRAW_URL 环境变量覆盖。
2026-07-17 00:44:20 +08:00
xsl c72e3ceda9 asdf 2026-07-17 00:32:13 +08:00
xsl 99ce21334a asdf 2026-07-17 00:26:47 +08:00
xsl 5fbc03a6df feat: 接口12/接口2 发际线重绘改走 local_test 外部 ComfyUI 服务
后端 generate_hairline_redraw 跳过内置 Flux-2 重绘,改为产出 final(接缝融合基底)
+ 纯红遮罩 PNG(redraw_band_mask_base64,遮罩区=(255,0,0,255)、其余全透明)。

接口2 female(generate_grow_results_swap) 取 final+遮罩后在后端调 local_test
(0716add-hair.json 工作流) 完成重绘,结果作为生发图返回;male 分支不变。

测试页 test_interface12.html / test_interface12_final.html 改为两阶段:
先生成 final+纯红遮罩,再前端调 local_test 重绘并展示;color_match 默认不勾选。

local_test/app.py 加 CORS 头(OPTIONS 预检),支持浏览器跨域直连。
2026-07-17 00:00:15 +08:00
xsl 0bbb15d668 添加服务 2026-07-16 22:57:12 +08:00
xsl 632e75317b 接口6 增加字段 2026-07-16 12:38:10 +08:00
xsl 1cd4115b26 Merge branch 'main' of http://git.xiangsilian.com:3000/xsl/hair 2026-07-16 09:38:53 +08:00
xslandCursor e8a2c5a8a1 fix: 日志目录去掉硬编码 /home/xsl,改为基于仓库根解析(支持 HAIR_LOG_DIR 覆盖)
worker 部署到 /home/ubuntu 等其他路径时,原硬编码 /home/xsl/hair/log
会导致 Permission denied。改为相对仓库根,兼容多机部署。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-16 08:07:03 +08:00
xsl 0f8a7e27c0 部署线上5090时候的改动git commit -m 部署线上5090时候的改动。 2026-07-16 07:54:07 +08:00
xsl 12f34c44f2 修改发型为最终发型 2026-07-16 00:22:54 +08:00
xslandCursor a208fe88ec feat: 拆分接口11/12,新增接口12 final / final v2 精简重绘端点
- 接口11 移除重绘,仅生成 final;接口12 (grow_v2) 负责发际线带 Flux-2 重绘
- 接口12 重绘带改为发际线外推 band_lo_mult~band_hi_mult 倍 push(默认 0.5~1.5),页面可调
- 接口12 同时产出 A 整帧重绘 与 B 局部加发+全脸美颜(beauty_alpha 可调)
- 新增 grow_v2_final(整帧重绘)/ grow_v2_final_v2(B 局部+美颜)端点:仅需图片+发型 ID,其余用固化默认值(color_match 关闭)
- 配套精简测试页 test_interface12_final.html / test_interface12_final_v2.html / test_interface12.html
- 恢复接口11 调试页多频段与换发型可调参数、color_match 默认不勾选
- 删除旧脚本 batch_grow_v2.py / gen_report_hairline_v2.py / test_simple.html

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-16 00:04:36 +08:00
xsl 4001df2c34 save code 2026-07-15 01:16:32 +08:00
xsl 9386f84c88 docs: 同步默认提示词「加一点美颜」到文档/接入页/测试页
- docs/接口文档.md:接口2/3/5/7 参数表统一更新默认提示词,接口2/3/7
  补全此前缺失的 prompt 参数行;顺带修正接口7 输出表 image_url 描述
  为透明 PNG(上一轮透明 PNG 改动的遗漏)
- static/integration.html:接口2 描述句 + 接口7 字段表同步透明 PNG 描述
- static/test_interface2/3/7.html:prompt 输入框默认值同步更新
2026-07-13 23:46:40 +08:00
xsl d5397a6d6f chore: 接口2/3/5/7 生发 ComfyUI 默认提示词加「加一点美颜」
将接口2(/api/v1/hair/grow)、接口3(/api/v1/hair/grow-b)、
接口5(/api/v1/hairline/generate)、接口7(/api/v1/hair/grow-v2)的
prompt 参数默认值从「补充遮罩区域的头发」改为「补充遮罩区域的头发,加一点美颜」。
2026-07-13 23:41:42 +08:00
xsl 95c6a2d929 feat: 接口2/5 发际线叠图改为透明 PNG(仅曲线),生发图不变
接口2(/api/v1/hair/grow)的 image_url 和接口5(/api/v1/hairline/generate)
的 image_middle/high/low_url 从「原图+白线合成 JPG」改为「透明底 PNG(仅含
发际线曲线)」,前端需叠加原图显示。grown_image_url 生发图保持不变(ComfyUI
完整人像照片)。

实现:
- app.py 新增 _rgba_png_b64() 编码 RGBA 透明层为 PNG base64(保留 alpha)
- hairline/service.py 接口2/5 改用 build_overlay_layer(返回 RGBA 透明层)
  替代 render_hairline_overlay(合成到原图)
- 网关零改动:rewrite_base64_to_url 已按 \x89PNG 魔数嗅探落盘为 .png

测试页:test_interface2/5.html 改为「原图打底 + 透明PNG 绝对定位叠加」显示
(复用 .img-stack 结构,固定叠加无开关)。

文档:接口文档.md / integration.html 更新接口2/5 图片字段说明。
测试:43 passed,接口2 image_base64 改断言为 PNG 魔数,接口5 三档叠图同。
2026-07-13 23:38:55 +08:00
759 changed files with 11150 additions and 1113 deletions
+32
View File
@@ -49,3 +49,35 @@ image/test/
# 批量报告输出(生成图+原图,体积大,不入 git)
static/report_hairline_v2/
static/report_hairline_v2.zip
# local_test 运行期日志 / pid(不入 git)
local_test/hair_service.log
local_test/hair_service.pid
# benchmark 原始输出(含结果图+原图,体积大,不入 git)
benchmark_out/
# benchmark 部署的 HTML 报告(图片 base64 内嵌,体积大,不入 git)
static/hairstyle_thumbs/
# 网关运行期日志(不入 git
gateway.log
# 工作流备份文件(不入 git
*.json.bak.*
# 脸型测试素材(人像照片,体积大,不入 git;仅保留 6 张基准标注图)
face/test_img/脸型测试集合/
face/test_img/girl/
face/test_img/man/
# 脸型特征缓存(由 face/dump_features.py 生成,可随时重跑)
face/cache/
# 脸型报告输出(标注图体积大,不入 git)
static/face_shape_report/
static/face_shape_report.html
static/facetest_report/
static/facetest_report.html
static/facetest_all_report/
static/facetest_all_report.html
+327
View File
@@ -0,0 +1,327 @@
{
"16": {
"class_type": "UnetLoaderGGUF",
"inputs": {
"unet_name": "flux-2-klein-9b-Q4_K_M.gguf",
"weight_dtype": "fp8_e4m3fn_fast"
}
},
"3": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "flux2-vae.safetensors"
}
},
"61": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "qwen_3_8b_fp8mixed.safetensors",
"type": "flux2",
"device": "cpu"
}
},
"26": {
"class_type": "LoadImage",
"inputs": {
"image": "placeholder.png"
}
},
"60": {
"class_type": "JjkText",
"inputs": {
"text": "填充遮罩区域的头发"
}
},
"22": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"61",
0
],
"text": [
"60",
0
]
}
},
"31": {
"class_type": "easy imageSize",
"inputs": {
"image": [
"26",
0
]
}
},
"33": {
"class_type": "Mask Fill Holes",
"inputs": {
"masks": [
"26",
1
]
}
},
"36": {
"class_type": "Convert Masks to Images",
"inputs": {
"masks": [
"33",
0
]
}
},
"39": {
"class_type": "ImageScale",
"inputs": {
"image": [
"36",
0
],
"upscale_method": "nearest-exact",
"width": [
"31",
0
],
"height": [
"31",
1
],
"crop": "disabled"
}
},
"37": {
"class_type": "Image To Mask",
"inputs": {
"image": [
"39",
0
],
"method": "intensity"
}
},
"32": {
"class_type": "LayerUtility: ImageScaleByAspectRatio V2",
"inputs": {
"image": [
"26",
0
],
"mask": [
"37",
0
],
"aspect_ratio": "custom",
"proportional_width": [
"31",
0
],
"proportional_height": [
"31",
1
],
"fit": "letterbox",
"method": "lanczos",
"round_to_multiple": "8",
"scale_to_side": "None",
"scale_to_length": 1024,
"background_color": "#000000"
}
},
"44": {
"class_type": "ImageAndMaskPreview",
"inputs": {
"image": [
"32",
0
],
"mask": [
"32",
1
],
"mask_opacity": 1,
"mask_color": "FFFF00",
"pass_through": true
}
},
"14": {
"class_type": "GetImageSize+",
"inputs": {
"image": [
"44",
0
]
}
},
"13": {
"class_type": "VAEEncode",
"inputs": {
"pixels": [
"44",
0
],
"vae": [
"3",
0
]
}
},
"2": {
"class_type": "ModelSamplingFlux",
"inputs": {
"model": [
"16",
0
],
"max_shift": 1.15,
"base_shift": 0.5,
"width": [
"14",
0
],
"height": [
"14",
1
]
}
},
"19": {
"class_type": "FluxGuidance",
"inputs": {
"conditioning": [
"22",
0
],
"guidance": 1
}
},
"5": {
"class_type": "ReferenceLatent",
"inputs": {
"conditioning": [
"19",
0
],
"latent": [
"13",
0
]
}
},
"7": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"width": [
"14",
0
],
"height": [
"14",
1
],
"batch_size": 1
}
},
"1": {
"class_type": "BasicScheduler",
"inputs": {
"model": [
"2",
0
],
"scheduler": "simple",
"steps": 4,
"denoise": 1
}
},
"20": {
"class_type": "BasicGuider",
"inputs": {
"model": [
"2",
0
],
"conditioning": [
"5",
0
]
}
},
"6": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 0
}
},
"8": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler"
}
},
"9": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"noise": [
"6",
0
],
"guider": [
"20",
0
],
"sampler": [
"8",
0
],
"sigmas": [
"1",
0
],
"latent_image": [
"7",
0
]
}
},
"10": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"9",
0
],
"vae": [
"3",
0
]
}
},
"62": {
"class_type": "ColorMatch",
"inputs": {
"image_ref": [
"26",
0
],
"image_target": [
"10",
0
],
"method": "mkl",
"strength": 1,
"multithread": true
}
},
"17": {
"class_type": "SaveImage",
"inputs": {
"images": [
"62",
0
],
"filename_prefix": "hair_inpaint"
}
}
}
File diff suppressed because one or more lines are too long
+6 -6
View File
@@ -2,7 +2,7 @@
"1": {
"inputs": {
"scheduler": "simple",
"steps": 6,
"steps": 4,
"denoise": 1,
"model": [
"2",
@@ -170,10 +170,10 @@
},
"16": {
"inputs": {
"unet_name": "flux2.0/flux-2-klein-9b-fp8.safetensors",
"weight_dtype": "fp8_e4m3fn"
"unet_name": "flux-2-klein-9b-Q4_K_M.gguf",
"weight_dtype": "fp8_e4m3fn_fast"
},
"class_type": "UNETLoader",
"class_type": "UnetLoaderGGUF",
"_meta": {
"title": "UNet加载器"
}
@@ -410,7 +410,7 @@
},
"60": {
"inputs": {
"text": "补充遮罩区补充遮罩区域的头发,头发填满遮罩区域。发际线往下挡住额头"
"text": "充遮罩区域的头发"
},
"class_type": "JjkText",
"_meta": {
@@ -421,7 +421,7 @@
"inputs": {
"clip_name": "qwen_3_8b_fp8mixed.safetensors",
"type": "flux2",
"device": "default"
"device": "cpu"
},
"class_type": "CLIPLoader",
"_meta": {
+928 -164
View File
File diff suppressed because it is too large Load Diff
+50
View File
@@ -0,0 +1,50 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""快速测试:3张图×花瓣发型×896分辨率,新提示词"填充遮罩区域的头发"
预热1次+正式1次。
"""
import base64, json, os, time
from pathlib import Path
import requests
API = "http://127.0.0.1:8187/api/v1/debug/grow-timing"
TOKEN = "dev-shared-secret-2026"
PROMPT = "填充遮罩区域的头发"
OUT = Path("/home/ubuntu/hair/benchmark_out/bench6")
OUT.mkdir(parents=True, exist_ok=True)
IMGS = [
("asdf", "/home/ubuntu/hair/image/asdf.jpg"),
("qwer", "/home/ubuntu/hair/image/qwer.jpg"),
("girl5", "/home/ubuntu/hair/image/girl_img/girl5.jpg"),
]
def call(img_path, save_grown=None, timeout=300):
data = {"hair_style": "2", "webui_steps": "15", "redraw_max_side": "896", "redraw_prompt": PROMPT}
t0 = time.perf_counter()
with open(img_path, "rb") as f:
r = requests.post(API, headers={"X-Internal-Token": TOKEN},
files={"image_file": (os.path.basename(img_path), f, "image/jpeg")},
data=data, timeout=timeout)
wall = time.perf_counter() - t0
j = r.json()
d = j["data"]; hs = d["per_hairstyle"][0]
if save_grown and hs.get("grown_b64"):
b = hs["grown_b64"].split(",")[1] if "," in hs["grown_b64"] else hs["grown_b64"]
open(save_grown, "wb").write(base64.b64decode(b))
return {"ok": hs.get("ok"), "total_ms": d["total_ms"], "comfy_ms": hs.get("comfyui_redraw_ms"),
"grown_path": str(save_grown) if save_grown and hs.get("ok") else None}
results = []
for ilabel, ipath in IMGS:
print(f"预热 {ilabel}...", flush=True)
call(ipath)
save = OUT / f"{ilabel}_flower_896.jpg"
print(f"正式 {ilabel}...", flush=True)
r = call(ipath, save_grown=save)
r["img"] = ilabel
print(f" -> total={r['total_ms']}ms ok={r['ok']}", flush=True)
results.append(r)
json.dump({"prompt": PROMPT, "results": results}, open(OUT/"results.json","w"), ensure_ascii=False, indent=2)
print(f"\n✓ 完成 {sum(1 for r in results if r['ok'])}/3", flush=True)
+134
View File
@@ -0,0 +1,134 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""发型对比矩阵测试:3图×5发型=15行,每行10张图(4b@896×1 + 9b三模型×三分辨率×9)。
按模型分组跑(减少模型切换次数、降低OOM风险),结果重组为15行存JSON+生成报告。
"""
import base64
import json
import os
import subprocess
import time
from collections import defaultdict
from pathlib import Path
import requests
API = "http://127.0.0.1:8187/api/v1/hair/grow"
TOKEN = "dev-shared-secret-2026"
OUT = Path("/home/ubuntu/hair/benchmark_out/hairstyle")
OUT.mkdir(parents=True, exist_ok=True)
IMGS = [
("asdf", "/home/ubuntu/hair/image/asdf.jpg"),
("qwer", "/home/ubuntu/hair/image/qwer.jpg"),
("girl5", "/home/ubuntu/hair/image/girl_img/girl5.jpg"),
]
HAIRSTYLES = [
(1, "ellipse", "椭圆"), (2, "flower", "花瓣"), (3, "heart", "心形"),
(4, "straight", "直线"), (5, "wave", "波浪"),
]
# 按模型分组:每个模型对应其要跑的(分辨率,列标题)
MODEL_GROUPS = [
("flux-2-klein-4b-fp8.safetensors", [("896", "4B@896")]),
("flux2.0/flux-2-klein-9b-fp8.safetensors",
[("0", "9B-fp8@原图"), ("896", "9B-fp8@896"), ("640", "9B-fp8@640")]),
("flux-2-klein-9b-Q5_K_M.gguf",
[("0", "9B-Q5@原图"), ("896", "9B-Q5@896"), ("640", "9B-Q5@640")]),
("flux-2-klein-9b-Q4_K_M.gguf",
[("0", "9B-Q4@原图"), ("896", "9B-Q4@896"), ("640", "9B-Q4@640")]),
]
# 列顺序(4b在前,然后9b三模型)
COLUMN_TITLES = ["4B@896", "9B-fp8@原图", "9B-fp8@896", "9B-fp8@640",
"9B-Q5@原图", "9B-Q5@896", "9B-Q5@640",
"9B-Q4@原图", "9B-Q4@896", "9B-Q4@640"]
def gpu_used():
try:
out = subprocess.check_output(
["nvidia-smi", "--query-gpu=memory.used", "--format=csv,noheader,nounits"], timeout=10)
return int(out.decode().strip())
except Exception:
return 0
def call(img_path, hair_num, model_file, res_val):
fd = {"gender": "female", "hair_style": str(hair_num), "use_mask": "true",
"prompt": "填充遮罩区域的头发"}
if model_file:
fd["flux_model"] = model_file
if res_val != "":
fd["redraw_max_side"] = res_val
t0 = time.perf_counter()
peak = gpu_used()
err = None
grown_b64 = None
try:
with open(img_path, "rb") as f:
r = requests.post(API, headers={"X-Internal-Token": TOKEN},
files={"image_file": (os.path.basename(img_path), f, "image/jpeg")},
data=fd, timeout=300)
elapsed = time.perf_counter() - t0
peak = max(peak, gpu_used())
j = r.json()
if j.get("code") != 0:
err = f"code={j.get('code')} {j.get('message', '')[:60]}"
else:
res = j.get("data", {}).get("results", [])
if res and res[0].get("grown_image_base64"):
grown_b64 = res[0]["grown_image_base64"]
elif res:
err = "grown_image空"
else:
err = "无results"
except Exception as e:
elapsed = time.perf_counter() - t0
err = str(e)[:150]
return {"elapsed": elapsed, "gpu_peak": peak, "grown_b64": grown_b64, "error": err}
def main():
# 结果字典: results[(img, hair_num, column_title)] = {grown_path, elapsed, gpu_peak, error}
results = {}
total = len(IMGS) * len(HAIRSTYLES) * len(COLUMN_TITLES)
idx = 0
for mfile, res_list in MODEL_GROUPS:
mname = os.path.basename(mfile)
print(f"\n===== 切换到模型: {mname} =====", flush=True)
# 等模型切换稳定
time.sleep(2)
for ilabel, ipath in IMGS:
for hnum, hkey, hname in HAIRSTYLES:
for rval, ctitle in res_list:
idx += 1
print(f"[{idx}/{total}] {ilabel}|{hname}|{ctitle}", flush=True)
r = call(ipath, hnum, mfile, rval)
status = f"{r['elapsed']:.1f}s" if not r["error"] else r["error"][:40]
print(f" -> {status} peak={r['gpu_peak']}M", flush=True)
if r["grown_b64"]:
fname = f"{ilabel}_{hkey}_{ctitle.replace('@','_').replace('-','')}.jpg"
with open(OUT / fname, "wb") as gf:
gf.write(base64.b64decode(r["grown_b64"]))
r["grown_path"] = str(OUT / fname)
results[(ilabel, hnum, ctitle)] = r
# 重组为15行
rows = []
for ilabel, ipath in IMGS:
for hnum, hkey, hname in HAIRSTYLES:
cells = []
for ct in COLUMN_TITLES:
r = results.get((ilabel, hnum, ct), {"error": "未跑"})
cells.append({"title": ct, **{k: v for k, v in r.items() if k != "grown_b64"}})
rows.append({"img": ilabel, "img_path": ipath,
"hair_num": hnum, "hair_key": hkey, "hair_name": hname,
"cells": cells})
with open(OUT / "results.json", "w", encoding="utf-8") as f:
json.dump({"columns": COLUMN_TITLES, "rows": rows}, f, ensure_ascii=False, indent=2)
ok = sum(1 for row in rows for c in row["cells"] if not c.get("error"))
print(f"\n✓ 完成: {ok}/{total} 成功 -> {OUT/'results.json'}", flush=True)
if __name__ == "__main__":
main()
+128
View File
@@ -0,0 +1,128 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""把发型对比测试结果生成 HTML 报告。
15行(3图×5发型) × 10列(4b@896 + 9b三模型×三分辨率),每行首列=原图。
图片 base64 内嵌,自包含单文件。
"""
import base64
import json
import os
from pathlib import Path
OUT = Path("/home/ubuntu/hair/benchmark_out/hairstyle")
RESULTS = OUT / "results.json"
HTML = OUT / "report.html"
def img_src(path):
"""把绝对路径转成报告里的相对 URL(报告在 static/,图片在 static/bench/)。"""
if not path:
return None
p = str(path)
if "benchmark_out/hairstyle/" in p:
return "bench/hairstyle/" + os.path.basename(p)
if "benchmark_out/matrix/" in p:
return "bench/matrix/" + os.path.basename(p)
return None
def main():
d = json.load(open(RESULTS, encoding="utf-8"))
columns = d["columns"]
rows = d["rows"]
# 统计每列的平均耗时、峰值显存
col_stats = {}
for ct in columns:
times, peaks = [], []
for r in rows:
for c in r["cells"]:
if c.get("title") == ct and not c.get("error"):
times.append(c["elapsed"])
peaks.append(c["gpu_peak"])
col_stats[ct] = {
"avg_t": sum(times) / len(times) if times else 0,
"max_p": max(peaks) / 1024 if peaks else 0,
}
# 表头:原图 + 10列
headers = ['<th class="col-label">原图</th>']
for ct in columns:
s = col_stats[ct]
headers.append(
f'<th class="col-label"><div class="col-title">{ct}</div>'
f'<div class="col-stat">{s["avg_t"]:.0f}s · {s["max_p"]:.0f}G</div></th>'
)
# 表体:15行
body_rows = []
for r in rows:
# 发型+图标签
label = f'<div class="row-label">{r["img"]}<br><b>{r["hair_name"]}</b></div>'
# 原图
ORIG_SRC = {"asdf": "bench/orig/asdf.jpg", "qwer": "bench/orig/qwer.jpg", "girl5": "bench/orig/girl5.jpg"}
orig = ORIG_SRC.get(r["img"])
cells = [f'<td class="cell-orig"><div class="row-label-cell">{label}</div>'
f'<img class="orig-img" src="{orig}"></td>']
# 10个结果列
for ct in columns:
c = next((x for x in r["cells"] if x.get("title") == ct), {})
src = img_src(c.get("grown_path")) if not c.get("error") else None
if src:
cells.append(
f'<td class="cell-result"><img class="result-img" src="{src}" loading="lazy">'
f'<div class="cell-time">{c["elapsed"]:.1f}s</div></td>')
else:
cells.append(f'<td class="cell-result"><div class="na">⚠</div></td>')
body_rows.append(f'<tr>{"".join(cells)}</tr>')
html = f"""<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>发型对比测试报告 — 4模型×3分辨率</title>
<style>
* {{ box-sizing: border-box; margin: 0; padding: 0; }}
body {{ font-family: -apple-system, "Segoe UI", sans-serif; background: #f5f5f5; padding: 16px; }}
h1 {{ font-size: 20px; margin-bottom: 4px; }}
.subtitle {{ color: #888; font-size: 12px; margin-bottom: 12px; }}
.legend {{ background: #fff; border-radius: 8px; padding: 10px 16px; margin-bottom: 12px; font-size: 12px; color: #555; }}
.scroll-wrap {{ overflow-x: auto; }}
table {{ border-collapse: collapse; background: #fff; border-radius: 8px; overflow: hidden;
box-shadow: 0 1px 4px rgba(0,0,0,.06); }}
th, td {{ border: 1px solid #eee; padding: 6px; vertical-align: top; text-align: center; }}
th {{ background: #f9fafb; position: sticky; top: 0; }}
.col-label {{ min-width: 110px; max-width: 130px; }}
.col-title {{ font-size: 12px; font-weight: 700; color: #374151; }}
.col-stat {{ font-size: 10px; color: #9ca3af; margin-top: 2px; }}
.row-label {{ font-size: 11px; color: #6b7280; }}
.row-label b {{ color: #1f2937; }}
.row-label-cell {{ font-size: 11px; color: #6b7280; margin-bottom: 4px; }}
.row-label-cell b {{ color: #1f2937; font-size: 13px; }}
img {{ border-radius: 4px; max-width: 120px; max-height: 150px; object-fit: contain; background: #f3f4f6; }}
.orig-img {{ border: 2px solid #d1d5db; max-height: 130px; }}
.cell-time {{ font-size: 10px; color: #9ca3af; margin-top: 2px; }}
.na {{ color: #d1d5db; font-size: 16px; padding: 40px; }}
</style>
</head>
<body>
<h1>💇 发型对比测试报告</h1>
<p class="subtitle">接口2女性 · 3图×5发型=15行 · 每行: 4B@896(1) + 9B(fp8/Q5/Q4)×(原图/896/640)(9) · 150/150成功 · RTX3090</p>
<div class="legend">列标题下显示<b>平均耗时 · 峰值显存</b>。横向滚动查看更多列。原图列含图片名+发型名。</div>
<div class="scroll-wrap">
<table>
<tr>{"".join(headers)}</tr>
{"".join(body_rows)}
</table>
</div>
</body>
</html>"""
with open(HTML, "w", encoding="utf-8") as f:
f.write(html)
print(f"✓ 报告: {HTML} ({HTML.stat().st_size//1024} KB)")
if __name__ == "__main__":
main()
+129
View File
@@ -0,0 +1,129 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""接口2女性 花瓣形 单发型 4模型×3分辨率×3图×3次 矩阵测试。
调用本机 hair-worker (:8187) 的 /api/v1/hair/growgender=female, hair_style=2(花瓣形)。
每次记录:生发图、耗时、显存峰值。结果图存到 benchmark_out/matrix/,最后生成 HTML 报告。
"""
import base64
import json
import os
import subprocess
import sys
import time
from pathlib import Path
import requests
API = "http://127.0.0.1:8187/api/v1/hair/grow"
TOKEN = "dev-shared-secret-2026"
OUT = Path("/home/ubuntu/hair/benchmark_out/matrix")
OUT.mkdir(parents=True, exist_ok=True)
# 4 模型 × 3 分辨率 × 3 图 × 3 次
MODELS = [
("4b-fp8", "flux-2-klein-4b-fp8.safetensors"),
("9b-fp8", "flux2.0/flux-2-klein-9b-fp8.safetensors"),
("9b-Q5", "flux-2-klein-9b-Q5_K_M.gguf"),
("9b-Q4", "flux-2-klein-9b-Q4_K_M.gguf"),
]
RES = [("orig", "0"), ("640", "640"), ("896", "896")]
IMGS = [
("asdf", "/home/ubuntu/hair/image/asdf.jpg"),
("qwer", "/home/ubuntu/hair/image/qwer.jpg"),
("girl5", "/home/ubuntu/hair/image/girl_img/girl5.jpg"),
]
REPEAT = 3
def gpu_used():
"""返回当前显存已用 MiB。"""
try:
out = subprocess.check_output(
["nvidia-smi", "--query-gpu=memory.used", "--format=csv,noheader,nounits"],
timeout=10,
)
return int(out.decode().strip())
except Exception:
return 0
def call(img_path, model_file, res_val):
"""调一次接口2。返回 dict: ok/elapsed/grown_path/gpu_peak/error。"""
fd = {
"gender": "female",
"hair_style": "2", # 花瓣形
"use_mask": "true",
"prompt": "填充遮罩区域的头发",
}
if model_file:
fd["flux_model"] = model_file
if res_val != "":
fd["redraw_max_side"] = res_val
t0 = time.perf_counter()
peak = gpu_used()
err = None
grown_path = None
try:
with open(img_path, "rb") as f:
r = requests.post(
API, headers={"X-Internal-Token": TOKEN},
files={"image_file": (os.path.basename(img_path), f, "image/jpeg")},
data=fd, timeout=300,
)
elapsed = time.perf_counter() - t0
# 采样峰值(推理刚结束)
peak = max(peak, gpu_used())
j = r.json()
if j.get("code") != 0:
err = f"code={j.get('code')} {j.get('message','')}"
else:
res = j.get("data", {}).get("results", [])
if res and res[0].get("grown_image_base64"):
grown_path = OUT / f"tmp_grown.jpg"
with open(grown_path, "wb") as gf:
gf.write(base64.b64decode(res[0]["grown_image_base64"]))
elif res:
err = "grown_image_base64 为空"
else:
err = "无 results"
except Exception as e:
elapsed = time.perf_counter() - t0
err = str(e)[:200]
return {"elapsed": elapsed, "gpu_peak": peak, "grown_path": str(grown_path) if grown_path else None, "error": err}
def main():
results = [] # 每元素一个组合
total = len(MODELS) * len(RES) * len(IMGS) * REPEAT
idx = 0
for mlabel, mfile in MODELS:
for rlabel, rval in RES:
for ilabel, ipath in IMGS:
# 一个组合:3 次
runs = []
for rep in range(REPEAT):
idx += 1
print(f"[{idx}/{total}] {mlabel} | res={rlabel} | {ilabel} | rep{rep+1}", flush=True)
r = call(ipath, mfile, rval)
print(f" -> {r['elapsed']:.1f}s peak={r['gpu_peak']}MiB err={r['error']}", flush=True)
# 存每次的生发图
if r["grown_path"]:
save_to = OUT / f"{mlabel}_{rlabel}_{ilabel}_r{rep+1}.jpg"
os.replace(r["grown_path"], save_to)
r["grown_path"] = str(save_to)
runs.append(r)
results.append({
"model": mlabel, "model_file": mfile,
"res": rlabel, "res_val": rval,
"img": ilabel, "img_path": ipath,
"runs": runs,
})
# 存原始数据
with open(OUT / "results.json", "w", encoding="utf-8") as f:
json.dump(results, f, ensure_ascii=False, indent=2)
print(f"\n✓ 全部完成,原始数据 -> {OUT/'results.json'}", flush=True)
if __name__ == "__main__":
main()
+157
View File
@@ -0,0 +1,157 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""把 benchmark_out/matrix/results.json 生成 HTML 报告。
每个组合一行:原图 + 3次生发图 + 耗时/显存。
图片用 base64 内嵌(自包含单文件,便于部署)。
"""
import base64
import json
import os
from pathlib import Path
OUT = Path("/home/ubuntu/hair/benchmark_out/matrix")
RESULTS = OUT / "results.json"
HTML = OUT / "report.html"
RES_LABEL = {"orig": "原图", "640": "640", "896": "896(默认)"}
MODEL_LABEL = {
"4b-fp8": "4B fp8 (3.8G)",
"9b-fp8": "9B fp8 (8.8G)",
"9b-Q5": "9B Q5_K_M (6.6G)",
"9b-Q4": "9B Q4_K_M (5.6G)",
}
MODEL_ORDER = ["4b-fp8", "9b-Q4", "9b-Q5", "9b-fp8"]
def img_src(path):
"""把绝对路径转成报告里的相对 URL(报告在 static/,图片在 static/bench/)。"""
if not path:
return None
p = str(path)
# benchmark_out/matrix/xxx.jpg -> bench/matrix/xxx.jpg
if "benchmark_out/matrix/" in p:
return "bench/matrix/" + os.path.basename(p)
if "benchmark_out/hairstyle/" in p:
return "bench/hairstyle/" + os.path.basename(p)
return None
def thumb(src, alt="", cls=""):
if not src:
return f'<div class="na {cls}">⚠ 失败</div>'
return f'<img class="{cls}" src="{src}" alt="{alt}" loading="lazy">'
def main():
data = json.load(open(RESULTS, encoding="utf-8"))
# 原图相对路径映射(图片在 static/bench/orig/
ORIG_SRC = {"asdf": "bench/orig/asdf.jpg", "qwer": "bench/orig/qwer.jpg", "girl5": "bench/orig/girl5.jpg"}
# 统计:每个模型的平均耗时、平均峰值显存
stats = {}
for c in data:
m = c["model"]
stats.setdefault(m, {"times": [], "peaks": []})
for r in c["runs"]:
if not r["error"]:
stats[m]["times"].append(r["elapsed"])
stats[m]["peaks"].append(r["gpu_peak"])
rows_html = []
# 按模型顺序、分辨率顺序、图片顺序排列
for m in MODEL_ORDER:
mdata = [c for c in data if c["model"] == m]
for rlabel in ["orig", "640", "896"]:
for ilabel in ["asdf", "qwer", "girl5"]:
c = next((x for x in mdata if x["res"] == rlabel and x["img"] == ilabel), None)
if not c:
continue
# 3 次结果图
run_cells = []
for i, r in enumerate(c["runs"]):
src = img_src(r["grown_path"]) if not r["error"] else None
if src:
run_cells.append(
f'<div class="run-cell"><div class="run-label">第{i+1}次 · {r["elapsed"]:.1f}s</div>'
f'{thumb(src, f"r{i+1}", "result-img")}</div>'
)
else:
run_cells.append(
f'<div class="run-cell"><div class="run-label">第{i+1}次 · 失败</div>'
f'<div class="na">⚠ {r["error"][:30] if r["error"] else ""}</div></div>'
)
orig = ORIG_SRC.get(c["img"])
rows_html.append(f'''
<div class="combo-row">
<div class="cell-model">{MODEL_LABEL.get(m, m)}<div class="cell-sub">res={RES_LABEL.get(rlabel, rlabel)}</div></div>
<div class="cell-img">{thumb(orig, "原图", "orig-img")}<div class="run-label">{ilabel}</div></div>
<div class="cell-runs">{"".join(run_cells)}</div>
</div>''')
# 模型对比汇总
summary_rows = []
for m in MODEL_ORDER:
s = stats.get(m, {"times": [], "peaks": []})
if s["times"]:
avg_t = sum(s["times"]) / len(s["times"])
max_p = max(s["peaks"]) / 1024
summary_rows.append(
f"<tr><td>{MODEL_LABEL.get(m,m)}</td><td>{avg_t:.1f}s</td>"
f"<td>{max_p:.1f} GB</td><td>{len(s['times'])} 成功</td></tr>"
)
html = f"""<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Flux 模型矩阵测试报告 — 接口2女性花瓣形</title>
<style>
* {{ box-sizing: border-box; margin: 0; padding: 0; }}
body {{ font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif; background: #f5f5f5; color: #333; padding: 20px; }}
h1 {{ font-size: 22px; margin-bottom: 4px; }}
.subtitle {{ color: #888; font-size: 13px; margin-bottom: 16px; }}
.summary {{ background: #fff; border-radius: 10px; padding: 16px 20px; margin-bottom: 20px; box-shadow: 0 1px 4px rgba(0,0,0,.06); }}
.summary h2 {{ font-size: 16px; margin-bottom: 10px; }}
.summary table {{ border-collapse: collapse; width: 100%; font-size: 14px; }}
.summary th, .summary td {{ border: 1px solid #e5e7eb; padding: 8px 12px; text-align: left; }}
.summary th {{ background: #f9fafb; font-weight: 600; }}
.combo-row {{ display: flex; align-items: flex-start; gap: 12px; background: #fff; border-radius: 10px;
padding: 12px 16px; margin-bottom: 10px; box-shadow: 0 1px 3px rgba(0,0,0,.05); }}
.cell-model {{ min-width: 130px; font-weight: 700; font-size: 14px; padding-top: 6px; }}
.cell-sub {{ font-weight: 400; font-size: 12px; color: #6b7280; margin-top: 2px; }}
.cell-img {{ min-width: 160px; text-align: center; }}
.cell-runs {{ display: flex; gap: 10px; flex: 1; }}
.run-cell {{ text-align: center; }}
.run-label {{ font-size: 11px; color: #6b7280; margin-bottom: 4px; }}
img {{ border-radius: 6px; max-height: 200px; max-width: 100%; object-fit: contain; background: #f9fafb; }}
.orig-img {{ max-height: 180px; border: 2px solid #e5e7eb; }}
.result-img {{ max-height: 200px; }}
.na {{ color: #d1d5db; font-size: 12px; padding: 40px 20px; background: #f9fafb; border-radius: 6px; width: 150px; }}
</style>
</head>
<body>
<h1>💇 Flux 模型矩阵测试报告</h1>
<p class="subtitle">接口2女性 · 花瓣形发型 · 4模型 × 3分辨率 × 3图 × 3次 = 108 次 · RTX 3090 24GB</p>
<div class="summary">
<h2>📊 模型对比汇总</h2>
<table>
<tr><th>模型</th><th>平均耗时</th><th>峰值显存</th><th>成功次数</th></tr>
{"".join(summary_rows)}
</table>
</div>
<h2 style="font-size:16px;margin:24px 0 12px">🖼️ 各组合对比(每行:原图 + 3次生发结果)</h2>
{"".join(rows_html)}
</body>
</html>"""
with open(HTML, "w", encoding="utf-8") as f:
f.write(html)
print(f"✓ 报告已生成: {HTML} ({HTML.stat().st_size//1024} KB)")
if __name__ == "__main__":
main()
+99
View File
@@ -0,0 +1,99 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""分辨率对比测试:4图×5发型=20行,每行4种分辨率(不缩放/896/768/640)steps=15。
热数据:每个组合预热1次(丢弃)+正式1次。OOM的跳过记录为失败。
"""
import base64
import json
import os
import time
from pathlib import Path
import requests
API = "http://127.0.0.1:8187/api/v1/debug/grow-timing"
TOKEN = "dev-shared-secret-2026"
OUT = Path("/home/ubuntu/hair/benchmark_out/bench3")
OUT.mkdir(parents=True, exist_ok=True)
IMGS = [
("asdf", "/home/ubuntu/hair/image/asdf.jpg"),
("qwer", "/home/ubuntu/hair/image/qwer.jpg"),
("girl2", "/home/ubuntu/hair/image/girl_img/girl2.jpg"),
("girl5", "/home/ubuntu/hair/image/girl_img/girl5.jpg"),
]
HAIRSTYLES = [
(1, "ellipse", "椭圆"), (2, "flower", "花瓣"), (3, "heart", "心形"),
(4, "straight", "直线"), (5, "wave", "波浪"),
]
# 分辨率档:0=不缩放(原图)
RES_LIST = [("orig", "0"), ("896", "896"), ("768", "768"), ("640", "640")]
RES_TITLES = ["原图(不缩放)", "896", "768", "640"]
STEPS = 15
def call(img_path, hair_num, redraw_max_side, save_grown=None, timeout=300):
data = {"hair_style": str(hair_num), "webui_steps": str(STEPS),
"redraw_max_side": str(redraw_max_side)}
t0 = time.perf_counter()
try:
with open(img_path, "rb") as f:
r = requests.post(API, headers={"X-Internal-Token": TOKEN},
files={"image_file": (os.path.basename(img_path), f, "image/jpeg")},
data=data, timeout=timeout)
wall = time.perf_counter() - t0
j = r.json()
if j.get("code") != 0:
return {"ok": False, "error": j.get("message", "")[:80], "wall": wall}
d = j["data"]
hs = d["per_hairstyle"][0]
if save_grown and hs.get("grown_b64"):
b = hs["grown_b64"].split(",")[1] if "," in hs["grown_b64"] else hs["grown_b64"]
with open(save_grown, "wb") as gf:
gf.write(base64.b64decode(b))
return {
"ok": hs.get("ok", False), "wall": wall,
"total_ms": d["total_ms"], "swap_ms": hs.get("swap_ms"),
"comfy_ms": hs.get("comfyui_redraw_ms"),
"error": hs.get("error"),
}
except Exception as e:
return {"ok": False, "error": str(e)[:80], "wall": time.perf_counter() - t0}
def main():
rows = []
total = len(IMGS) * len(HAIRSTYLES) * len(RES_LIST) * 2
idx = 0
for ilabel, ipath in IMGS:
for hnum, hkey, hname in HAIRSTYLES:
cells = []
for (rlabel, rval), rtitle in zip(RES_LIST, RES_TITLES):
# 预热
idx += 1
print(f"[{idx}/{total}] 预热 {ilabel}|{hname}|{rtitle}", flush=True)
try:
call(ipath, hnum, rval, timeout=120)
except Exception:
pass # 预热失败(可能OOM)不中断
# 正式
idx += 1
save = OUT / f"{ilabel}_{hkey}_{rlabel}.jpg"
print(f"[{idx}/{total}] 正式 {ilabel}|{hname}|{rtitle}", flush=True)
r = call(ipath, hnum, rval, save_grown=save, timeout=300)
r["res_label"] = rlabel; r["res_title"] = rtitle
r["grown_path"] = str(save) if r.get("ok") else None
status = f"{r.get('total_ms')}ms" if r.get("ok") else f"FAIL:{r.get('error','')[:30]}"
print(f" -> {status}", flush=True)
cells.append(r)
rows.append({"img": ilabel, "img_path": ipath,
"hair_num": hnum, "hair_key": hkey, "hair_name": hname,
"cells": cells})
with open(OUT / "results.json", "w", encoding="utf-8") as f:
json.dump({"res_titles": RES_TITLES, "rows": rows}, f, ensure_ascii=False, indent=2)
ok = sum(1 for row in rows for c in row["cells"] if c.get("ok"))
print(f"\n✓ 完成: {ok}/{len(rows)*len(RES_LIST)} 成功 -> {OUT/'results.json'}", flush=True)
if __name__ == "__main__":
main()
+103
View File
@@ -0,0 +1,103 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""生成分辨率对比报告:20行(4图×5发型) × 4列(原图不缩放/896/768/640)。"""
import json
import os
from collections import defaultdict
from pathlib import Path
OUT = Path("/home/ubuntu/hair/benchmark_out/bench3")
RESULTS = OUT / "results.json"
HTML = OUT / "report.html"
def img_src(path):
if not path or not os.path.isfile(path):
return None
return "bench3/" + os.path.basename(path)
def main():
d = json.load(open(RESULTS, encoding="utf-8"))
titles = d["res_titles"]
rows = d["rows"]
# 各分辨率平均耗时
col_stats = defaultdict(lambda: {"total": [], "comfy": []})
for r in rows:
for c in r["cells"]:
if c.get("ok"):
col_stats[c["res_title"]]["total"].append(c["total_ms"])
col_stats[c["res_title"]]["comfy"].append(c.get("comfy_ms", 0))
# 表头
headers = ['<th class="col-label">原图</th>']
for t in titles:
s = col_stats.get(t)
avg = sum(s["total"]) // len(s["total"]) if s and s["total"] else 0
headers.append(f'<th class="col-label"><div class="col-title">{t}</div>'
f'<div class="col-stat">均{avg/1000:.1f}s</div></th>')
# 表体
body_rows = []
for r in rows:
label = f'<div class="row-label">{r["img"]}<br><b>{r["hair_name"]}</b></div>'
# 原图缩略图(用 orig 档的结果当原图展示,或用原图文件)
orig_cell = f'<td class="cell-orig"><div class="row-label-cell">{label}</div></td>'
cells = [orig_cell]
for c in r["cells"]:
src = img_src(c.get("grown_path")) if c.get("ok") else None
if src:
t = c.get("total_ms", 0)
cells.append(f'<td class="cell-result"><img class="result-img" src="{src}" loading="lazy">'
f'<div class="cell-time">{t/1000:.1f}s</div></td>')
else:
cells.append(f'<td class="cell-result"><div class="na">⚠<br>{c.get("error","")[:20]}</div></td>')
body_rows.append(f'<tr>{"".join(cells)}</tr>')
html = f"""<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>重绘分辨率对比报告 — steps=15</title>
<style>
* {{ box-sizing: border-box; margin: 0; padding: 0; }}
body {{ font-family: -apple-system, "Segoe UI", sans-serif; background: #f5f5f5; padding: 16px; }}
h1 {{ font-size: 20px; margin-bottom: 4px; }}
.subtitle {{ color: #888; font-size: 12px; margin-bottom: 12px; }}
.legend {{ background: #fff; border-radius: 8px; padding: 10px 16px; margin-bottom: 12px; font-size: 12px; color: #555; }}
.scroll-wrap {{ overflow-x: auto; }}
table {{ border-collapse: collapse; background: #fff; border-radius: 8px; overflow: hidden; box-shadow: 0 1px 4px rgba(0,0,0,.06); }}
th, td {{ border: 1px solid #eee; padding: 6px; vertical-align: top; text-align: center; }}
th {{ background: #f9fafb; position: sticky; top: 0; }}
.col-label {{ min-width: 130px; max-width: 150px; }}
.col-title {{ font-size: 12px; font-weight: 700; color: #374151; }}
.col-stat {{ font-size: 10px; color: #9ca3af; margin-top: 2px; }}
.row-label {{ font-size: 11px; color: #6b7280; }}
.row-label b {{ color: #1f2937; }}
img {{ border-radius: 4px; max-width: 130px; max-height: 160px; object-fit: contain; background: #f3f4f6; }}
.cell-time {{ font-size: 10px; color: #9ca3af; margin-top: 2px; }}
.na {{ color: #d1d5db; font-size: 12px; padding: 40px 10px; }}
</style>
</head>
<body>
<h1>📊 重绘分辨率对比报告</h1>
<p class="subtitle">4图×5发型=20行 · 每行4分辨率(原图不缩放/896/768/640) · steps=15 · 热数据 · 80/80成功 · 峰值21.2GB · 0 OOM</p>
<div class="legend">列标题下显示<b>平均总耗时</b>。横向滚动查看。原图列含图片名+发型名。每格下方为该次总耗时。</div>
<div class="scroll-wrap">
<table>
<tr>{"".join(headers)}</tr>
{"".join(body_rows)}
</table>
</div>
</body>
</html>"""
with open(HTML, "w", encoding="utf-8") as f:
f.write(html)
print(f"✓ 报告: {HTML} ({HTML.stat().st_size // 1024} KB)")
if __name__ == "__main__":
main()
+98
View File
@@ -0,0 +1,98 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""分辨率对比测试(新提示词版):4图×5发型=20行,每行4种分辨率,steps=15。
提示词固定为 "填充遮罩区域的头发"
热数据:预热1次+正式1次。
"""
import base64
import json
import os
import time
from pathlib import Path
import requests
API = "http://127.0.0.1:8187/api/v1/debug/grow-timing"
TOKEN = "dev-shared-secret-2026"
PROMPT = "填充遮罩区域的头发"
OUT = Path("/home/ubuntu/hair/benchmark_out/bench7")
OUT.mkdir(parents=True, exist_ok=True)
IMGS = [
("asdf", "/home/ubuntu/hair/image/asdf.jpg"),
("qwer", "/home/ubuntu/hair/image/qwer.jpg"),
("girl2", "/home/ubuntu/hair/image/girl_img/girl2.jpg"),
("girl5", "/home/ubuntu/hair/image/girl_img/girl5.jpg"),
]
HAIRSTYLES = [
(1, "ellipse", "椭圆"), (2, "flower", "花瓣"), (3, "heart", "心形"),
(4, "straight", "直线"), (5, "wave", "波浪"),
]
RES_LIST = [("orig", "0"), ("896", "896"), ("768", "768"), ("640", "640")]
RES_TITLES = ["原图(不缩放)", "896", "768", "640"]
STEPS = 15
def call(img_path, hair_num, redraw_max_side, save_grown=None, timeout=300):
data = {"hair_style": str(hair_num), "webui_steps": str(STEPS),
"redraw_max_side": str(redraw_max_side), "redraw_prompt": PROMPT}
t0 = time.perf_counter()
try:
with open(img_path, "rb") as f:
r = requests.post(API, headers={"X-Internal-Token": TOKEN},
files={"image_file": (os.path.basename(img_path), f, "image/jpeg")},
data=data, timeout=timeout)
wall = time.perf_counter() - t0
j = r.json()
if j.get("code") != 0:
return {"ok": False, "error": j.get("message", "")[:80], "wall": wall}
d = j["data"]
hs = d["per_hairstyle"][0]
if save_grown and hs.get("grown_b64"):
b = hs["grown_b64"].split(",")[1] if "," in hs["grown_b64"] else hs["grown_b64"]
with open(save_grown, "wb") as gf:
gf.write(base64.b64decode(b))
return {
"ok": hs.get("ok", False), "wall": wall,
"total_ms": d["total_ms"], "swap_ms": hs.get("swap_ms"),
"comfy_ms": hs.get("comfyui_redraw_ms"),
"error": hs.get("error"),
}
except Exception as e:
return {"ok": False, "error": str(e)[:80], "wall": time.perf_counter() - t0}
def main():
rows = []
total = len(IMGS) * len(HAIRSTYLES) * len(RES_LIST) * 2
idx = 0
for ilabel, ipath in IMGS:
for hnum, hkey, hname in HAIRSTYLES:
cells = []
for (rlabel, rval), rtitle in zip(RES_LIST, RES_TITLES):
idx += 1
print(f"[{idx}/{total}] 预热 {ilabel}|{hname}|{rtitle}", flush=True)
try:
call(ipath, hnum, rval, timeout=120)
except Exception:
pass
idx += 1
save = OUT / f"{ilabel}_{hkey}_{rlabel}.jpg"
print(f"[{idx}/{total}] 正式 {ilabel}|{hname}|{rtitle}", flush=True)
r = call(ipath, hnum, rval, save_grown=save, timeout=300)
r["res_label"] = rlabel; r["res_title"] = rtitle
r["grown_path"] = str(save) if r.get("ok") else None
status = f"{r.get('total_ms')}ms" if r.get("ok") else f"FAIL:{r.get('error','')[:30]}"
print(f" -> {status}", flush=True)
cells.append(r)
rows.append({"img": ilabel, "img_path": ipath,
"hair_num": hnum, "hair_key": hkey, "hair_name": hname,
"cells": cells})
with open(OUT / "results.json", "w", encoding="utf-8") as f:
json.dump({"res_titles": RES_TITLES, "prompt": PROMPT, "rows": rows}, f, ensure_ascii=False, indent=2)
ok = sum(1 for row in rows for c in row["cells"] if c.get("ok"))
print(f"\n✓ 完成: {ok}/{len(rows)*len(RES_LIST)} 成功 -> {OUT/'results.json'}", flush=True)
if __name__ == "__main__":
main()
+121
View File
@@ -0,0 +1,121 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""swap步数 + 重绘分辨率 对比测试(热数据)。
每个组合: 预热1次(丢弃) + 正式测1次(取热数据)。
B维度: steps=10/15/20 (分辨率固定896)
C维度: 分辨率=640/896/1024 (steps固定15)
4图×2发型=8组 × 6档 × 2次(预热+正式) = 96次
"""
import base64
import json
import os
import time
from pathlib import Path
import requests
API = "http://127.0.0.1:8187/api/v1/debug/grow-timing"
TOKEN = "dev-shared-secret-2026"
OUT = Path("/home/ubuntu/hair/benchmark_out/bench2")
OUT.mkdir(parents=True, exist_ok=True)
IMGS = [
("asdf", "/home/ubuntu/hair/image/asdf.jpg"),
("qwer", "/home/ubuntu/hair/image/qwer.jpg"),
("girl2", "/home/ubuntu/hair/image/girl_img/girl2.jpg"),
("girl5", "/home/ubuntu/hair/image/girl_img/girl5.jpg"),
]
HAIRSTYLES = [(5, "wave", "波浪"), (3, "heart", "心形")]
# B维度: swap步数对比 (分辨率固定896)
B_STEPS = [10, 15, 20]
# C维度: 重绘分辨率对比 (steps固定15)
C_RES = [640, 896, 1024]
def call(img_path, hair_num, webui_steps=None, redraw_max_side=None, save_grown=None):
"""调调试接口。返回 dict。save_grown 非None时把结果图存到该路径。"""
data = {"hair_style": str(hair_num)}
if webui_steps is not None:
data["webui_steps"] = str(webui_steps)
if redraw_max_side is not None:
data["redraw_max_side"] = str(redraw_max_side)
t0 = time.perf_counter()
try:
with open(img_path, "rb") as f:
r = requests.post(API, headers={"X-Internal-Token": TOKEN},
files={"image_file": (os.path.basename(img_path), f, "image/jpeg")},
data=data, timeout=300)
wall = time.perf_counter() - t0
j = r.json()
if j.get("code") != 0:
return {"ok": False, "error": j.get("message", "")[:100], "wall": wall}
d = j["data"]
hs = d["per_hairstyle"][0]
if save_grown and hs.get("grown_b64"):
b = hs["grown_b64"].split(",")[1] if "," in hs["grown_b64"] else hs["grown_b64"]
with open(save_grown, "wb") as gf:
gf.write(base64.b64decode(b))
return {
"ok": hs.get("ok", False), "wall": wall,
"total_ms": d["total_ms"], "ctx_ms": d["extract_context_ms"],
"mask_ms": hs.get("mask_ms"), "swap_ms": hs.get("swap_ms"),
"blend_ms": hs.get("blend_ms"), "comfy_ms": hs.get("comfyui_redraw_ms"),
"error": hs.get("error"),
}
except Exception as e:
return {"ok": False, "error": str(e)[:100], "wall": time.perf_counter() - t0}
def main():
results = {"B_steps": [], "C_res": []}
total_calls = len(IMGS) * len(HAIRSTYLES) * (len(B_STEPS) + len(C_RES)) * 2
idx = 0
# ===== B维度: swap步数对比 (分辨率固定896) =====
print("\n===== B维度: swap步数对比 (分辨率=896) =====", flush=True)
for steps in B_STEPS:
print(f"\n--- steps={steps} ---", flush=True)
for ilabel, ipath in IMGS:
for hnum, hkey, hname in HAIRSTYLES:
# 预热(丢弃)
idx += 1
print(f"[{idx}/{total_calls}] 预热 {ilabel}|{hname}|steps={steps}", flush=True)
call(ipath, hnum, webui_steps=steps, redraw_max_side=896)
# 正式(热数据)
idx += 1
save = OUT / f"B_steps{steps}_{ilabel}_{hkey}.jpg"
print(f"[{idx}/{total_calls}] 正式 {ilabel}|{hname}|steps={steps}", flush=True)
r = call(ipath, hnum, webui_steps=steps, redraw_max_side=896, save_grown=save)
r["steps"] = steps; r["img"] = ilabel; r["hair"] = hkey; r["hair_name"] = hname
r["grown_path"] = str(save) if r.get("ok") else None
print(f" -> total={r.get('total_ms')}ms swap={r.get('swap_ms')}ms comfy={r.get('comfy_ms')}ms ok={r.get('ok')}", flush=True)
results["B_steps"].append(r)
# ===== C维度: 重绘分辨率对比 (steps固定15) =====
print("\n===== C维度: 重绘分辨率对比 (steps=15) =====", flush=True)
for res in C_RES:
print(f"\n--- res={res} ---", flush=True)
for ilabel, ipath in IMGS:
for hnum, hkey, hname in HAIRSTYLES:
idx += 1
print(f"[{idx}/{total_calls}] 预热 {ilabel}|{hname}|res={res}", flush=True)
call(ipath, hnum, webui_steps=15, redraw_max_side=res)
idx += 1
save = OUT / f"C_res{res}_{ilabel}_{hkey}.jpg"
print(f"[{idx}/{total_calls}] 正式 {ilabel}|{hname}|res={res}", flush=True)
r = call(ipath, hnum, webui_steps=15, redraw_max_side=res, save_grown=save)
r["res"] = res; r["img"] = ilabel; r["hair"] = hkey; r["hair_name"] = hname
r["grown_path"] = str(save) if r.get("ok") else None
print(f" -> total={r.get('total_ms')}ms swap={r.get('swap_ms')}ms comfy={r.get('comfy_ms')}ms ok={r.get('ok')}", flush=True)
results["C_res"].append(r)
with open(OUT / "results.json", "w", encoding="utf-8") as f:
json.dump(results, f, ensure_ascii=False, indent=2)
ok = sum(1 for r in results["B_steps"] + results["C_res"] if r.get("ok"))
print(f"\n✓ 完成: {ok}/{len(results['B_steps'])+len(results['C_res'])} 成功 -> {OUT/'results.json'}", flush=True)
if __name__ == "__main__":
main()
+157
View File
@@ -0,0 +1,157 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""生成 swap步数 + 重绘分辨率 对比报告 HTML。"""
import json
import os
from collections import defaultdict
from pathlib import Path
OUT = Path("/home/ubuntu/hair/benchmark_out/bench2")
RESULTS = OUT / "results.json"
HTML = OUT / "report.html"
def img_src(path):
if not path or not os.path.isfile(path):
return None
# benchmark_out/bench2/xxx.jpg -> bench2/xxx.jpg (报告在 static/ 下部署时调整)
p = str(path)
return "bench2/" + os.path.basename(p)
def main():
d = json.load(open(RESULTS, encoding="utf-8"))
b_data = d["B_steps"] # steps 对比
c_data = d["C_res"] # 分辨率对比
# B维度聚合
by_steps = defaultdict(list)
for r in b_data:
by_steps[r["steps"]].append(r)
b_summary = []
for s in sorted(by_steps):
rs = by_steps[s]
b_summary.append({
"label": f"steps={s}", "n": len(rs),
"swap": sum(r["swap_ms"] for r in rs) // len(rs),
"total": sum(r["total_ms"] for r in rs) // len(rs),
})
# C维度聚合
by_res = defaultdict(list)
for r in c_data:
by_res[r["res"]].append(r)
c_summary = []
for res in sorted(by_res):
rs = by_res[res]
c_summary.append({
"label": f"res={res}", "n": len(rs),
"comfy": sum(r["comfy_ms"] for r in rs) // len(rs),
"total": sum(r["total_ms"] for r in rs) // len(rs),
})
# B维度明细行(每图每发型每步数)
b_rows = []
for r in sorted(b_data, key=lambda x: (x["img"], x["hair"], x["steps"])):
src = img_src(r.get("grown_path"))
b_rows.append(f"""<tr>
<td>{r['img']}</td><td>{r['hair_name']}</td><td>{r['steps']}</td>
<td>{r.get('swap_ms','?')}</td><td>{r.get('comfy_ms','?')}</td><td>{r.get('total_ms','?')}</td>
<td>{f'<img src="{src}" loading="lazy">' if src else ''}</td></tr>""")
# C维度明细行
c_rows = []
for r in sorted(c_data, key=lambda x: (x["img"], x["hair"], x["res"])):
src = img_src(r.get("grown_path"))
c_rows.append(f"""<tr>
<td>{r['img']}</td><td>{r['hair_name']}</td><td>{r['res']}</td>
<td>{r.get('swap_ms','?')}</td><td>{r.get('comfy_ms','?')}</td><td>{r.get('total_ms','?')}</td>
<td>{f'<img src="{src}" loading="lazy">' if src else ''}</td></tr>""")
def bar_row(label, val, max_val, color, unit="ms"):
pct = max(1, val / max_val * 100) if max_val else 0
return f'<div class="step-row"><div class="step-name">{label}</div>' \
f'<div class="step-bar-wrap"><div class="step-bar {color}" style="width:{pct}%">{val}{unit}</div></div>' \
f'<div class="step-time">{val}{unit}</div></div>'
# B维度汇总条形图
b_max_swap = max(s["swap"] for s in b_summary)
b_bars = "".join(bar_row(s["label"], s["swap"], b_max_swap, "c-swap") for s in b_summary)
b_max_total = max(s["total"] for s in b_summary)
b_total_bars = "".join(bar_row(s["label"], s["total"], b_max_total, "c-total") for s in b_summary)
# C维度汇总条形图
c_max_comfy = max(s["comfy"] for s in c_summary)
c_bars = "".join(bar_row(s["label"], s["comfy"], c_max_comfy, "c-comfy") for s in c_summary)
c_max_total = max(s["total"] for s in c_summary)
c_total_bars = "".join(bar_row(s["label"], s["total"], c_max_total, "c-total") for s in c_summary)
html = f"""<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>swap步数 + 重绘分辨率 对比报告</title>
<style>
* {{ box-sizing: border-box; margin: 0; padding: 0; }}
body {{ font-family: -apple-system, "Segoe UI", sans-serif; background: #f5f5f5; padding: 16px; color: #333; }}
h1 {{ font-size: 20px; margin-bottom: 4px; }}
h2 {{ font-size: 16px; margin: 20px 0 10px; }}
.subtitle {{ color: #888; font-size: 12px; margin-bottom: 14px; }}
.card {{ background: #fff; border-radius: 10px; box-shadow: 0 1px 4px rgba(0,0,0,.06); margin-bottom: 16px; overflow: hidden; }}
.card-header {{ font-weight: 700; font-size: 14px; padding: 12px 18px; border-bottom: 1px solid #f0f0f0; background: #fafafa; }}
.card-body {{ padding: 18px; }}
.summary-grid {{ display: grid; grid-template-columns: 1fr 1fr; gap: 16px; }}
.step-row {{ display: flex; align-items: center; gap: 10px; margin-bottom: 8px; font-size: 13px; }}
.step-name {{ width: 100px; flex-shrink: 0; font-weight: 600; }}
.step-bar-wrap {{ flex: 1; background: #f3f4f6; border-radius: 4px; height: 24px; min-width: 200px; }}
.step-bar {{ height: 100%; border-radius: 4px; display: flex; align-items: center; padding-left: 8px; color: #fff; font-size: 11px; font-weight: 600; min-width: 2px; }}
.step-time {{ width: 70px; text-align: right; font-weight: 600; flex-shrink: 0; font-variant-numeric: tabular-nums; }}
.c-swap {{ background: #f59e0b; }} .c-comfy {{ background: #ef4444; }} .c-total {{ background: #2563eb; }}
table {{ border-collapse: collapse; width: 100%; font-size: 12px; }}
th, td {{ border: 1px solid #eee; padding: 5px 8px; text-align: center; }}
th {{ background: #f9fafb; font-weight: 600; position: sticky; top: 0; }}
td img {{ max-height: 100px; max-width: 80px; border-radius: 4px; }}
.scroll {{ max-height: 400px; overflow: auto; }}
.note {{ background: #fef3c7; border-radius: 8px; padding: 10px 14px; font-size: 12px; color: #92400e; margin-top: 10px; }}
</style>
</head>
<body>
<h1>📊 swap步数 + 重绘分辨率 对比报告</h1>
<p class="subtitle">4图(asdf/qwer/girl2/girl5) × 2发型(波浪/心形) · 热数据(预热后取第2次) · 48/48成功 · 峰值20.6GB · 0 OOM</p>
<div class="note">💡 结论速览: B维度 steps 10→20 swap从3.0s→3.9s(每步省~90ms)C维度 res 640比896省3s(comfy 4.3s vs 7.3s)1024与896接近。</div>
<h2>B维度:swap步数对比(分辨率固定896</h2>
<div class="summary-grid">
<div class="card"><div class="card-header">swap 耗时(越低越快)</div><div class="card-body">{b_bars}</div></div>
<div class="card"><div class="card-header">总耗时(越低越快)</div><div class="card-body">{b_total_bars}</div></div>
</div>
<h2>C维度:重绘分辨率对比(steps固定15</h2>
<div class="summary-grid">
<div class="card"><div class="card-header">ComfyUI重绘 耗时(越低越快)</div><div class="card-body">{c_bars}</div></div>
<div class="card"><div class="card-header">总耗时(越低越快)</div><div class="card-body">{c_total_bars}</div></div>
</div>
<h2>B维度明细(每图每发型每步数)</h2>
<div class="card"><div class="scroll"><table>
<tr><th>图片</th><th>发型</th><th>steps</th><th>swap(ms)</th><th>comfy(ms)</th><th>总(ms)</th><th>结果</th></tr>
{"".join(b_rows)}
</table></div></div>
<h2>C维度明细(每图每发型每分辨率)</h2>
<div class="card"><div class="scroll"><table>
<tr><th>图片</th><th>发型</th><th>res</th><th>swap(ms)</th><th>comfy(ms)</th><th>总(ms)</th><th>结果</th></tr>
{"".join(c_rows)}
</table></div></div>
</body>
</html>"""
with open(HTML, "w", encoding="utf-8") as f:
f.write(html)
print(f"✓ 报告: {HTML} ({HTML.stat().st_size // 1024} KB)")
if __name__ == "__main__":
main()
+15
View File
@@ -0,0 +1,15 @@
[Unit]
Description=ComfyUI (127.0.0.1:8188)
After=network-online.target
Wants=network-online.target
[Service]
Type=simple
User=ubuntu
WorkingDirectory=/home/ubuntu/ComfyUI
ExecStart=/home/ubuntu/ComfyUI/venv/bin/python main.py --listen 127.0.0.1 --port 8188 --cache-classic --fast
Restart=on-failure
RestartSec=5
[Install]
WantedBy=multi-user.target
Binary file not shown.

After

Width:  |  Height:  |  Size: 304 KiB

File diff suppressed because one or more lines are too long
@@ -0,0 +1,65 @@
{
"code": 0,
"message": "success",
"request_id": "mock-request-id",
"data": {
"hairline_id": "chang_zhixian",
"gen_backend": "swaphair",
"hairgrow_strength": 0.75,
"is_hr": false,
"seg_model": "segformer",
"mask_type": "pushed",
"erode_cm": 0.6,
"swap_mode": "ext_mask",
"blend_method": "multiband",
"edge_erode_px": 3,
"mb_levels": 5,
"hairline_push_cm": 1.0,
"hairline_edge": "column",
"denoising_strength": 0.6,
"color_match": true,
"color_match_strength": 1.0,
"mb_feather_px": 1,
"transition_band_px": -1,
"inpainting_fill": 1,
"mask_blur": 11,
"mask_dilate_scale": 1.0,
"px_per_cm": 47.5311,
"erode_px": 29,
"hair_pixels": 186798,
"closed_pixels": 191712,
"mask_pixels": 140299,
"image_size": {
"width": 1257,
"height": 1495
},
"timings_ms": {
"mask": 1462,
"swap": 5596,
"blend": 220
},
"redraw": {
"enabled": false
},
"_rid": "bc7205a4",
"steps": {
"input_base64": "<omitted 427407 chars>",
"baseline_overlay_base64": "<omitted 435895 chars>",
"upper_overlay_base64": "<omitted 384479 chars>",
"hair_seg_overlay_base64": "<omitted 428039 chars>",
"top_fill_overlay_base64": "",
"closed_overlay_base64": "",
"hairline_overlay_base64": "<omitted 445467 chars>",
"pushed_overlay_base64": "<omitted 452803 chars>",
"mask_overlay_base64": "<omitted 420375 chars>",
"mask_base64": "<omitted 8026 chars>",
"swap_raw_base64": "<omitted 340791 chars>",
"hard_paste_base64": "<omitted 420679 chars>",
"alpha_base64": "<omitted 7762 chars>",
"final_base64": "<omitted 415811 chars>",
"redraw_band_overlay_base64": "",
"redraw_a_base64": "",
"redraw_c_base64": ""
}
}
}
Binary file not shown.

After

Width:  |  Height:  |  Size: 5.7 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 319 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 304 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 314 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 326 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 308 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 313 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 5.9 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 308 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 332 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 250 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 282 KiB

+177
View File
@@ -0,0 +1,177 @@
# 接口3 B端生发 — 实现文档
> 文档日期:2026-07-18
---
## 一、接口概述
**接口3** 是 B端(医生/操作端)生发接口。医生在用户照片上手动用马克笔画出发际线后,只需上传这一张划线图,系统自动检测划线 → 生成遮罩 → 送 ComfyUI 生发,返回「植发3个月」效果图。
**与接口2 的核心区别**
| 特性 | 接口2(C端生发) | 接口3(B端生发) |
|------|----------------|----------------|
| 输入 | 原始照片 | 划线图(含手绘线) |
| 发际线来源 | 系统按发型模板自动生成 | 医生手绘标注 |
| 发型类型 | ellipse/flower/heart/straight/wave | custom(自定义) |
| 中间步骤 | extract_context + swapHair + ComfyUI重绘 | 划线检测 + 遮罩 + ComfyUI生发 |
| 是否调 change_hair | 是(女性流程) | 否 |
| ComfyUI 工作流 | 0716add-hair-api.json(重绘) | add_hair.json(生发) |
| 典型耗时 | ~11s | ~6-8s |
---
## 二、接口定义
### 路由
```
POST /api/v1/hair/grow-b
```
### 入参
| 参数 | 类型 | 必填 | 说明 |
|------|------|------|------|
| `marked_image_file` | UploadFile | 三选一 | 划线图片文件(JPG/PNG) |
| `marked_image_url` | str | 三选一 | 划线图片 URL |
| `marked_image_base64` | str | 三选一 | 划线图片 base64 |
| `use_mask` | bool | 否(默认True) | 是否自动检测划线并建遮罩。False时跳过检测,直接送划线图 |
| `prompt` | str | 否 | ComfyUI 提示词,默认"补充遮罩区域的头发,加一点美颜" |
### 返回
```json
{
"code": 0,
"message": "success",
"data": {
"hair_growth_image_base64": "iVBORw0KGgo...(生发图 JPG base64",
"hairline_type": "custom"
}
}
```
错误码:
- `1001`: 无法识别人像 / 未检测到发际线划线
- `1007`: 处理失败
- `1008`: 图片格式不支持
---
## 三、完整调用链
```
POST /api/v1/hair/grow-b
├─ app.py hair_grow_b() [app.py:929]
│ ├─ resolve_image_bytes() → marked_raw 解析图片(file/url/base64三选一)
│ ├─ cv2.imdecode → marked_bgr 解码为 BGR
│ └─ run_in_threadpool(generate_grow_b, ...)
├─ service.py generate_grow_b(marked_bgr, use_mask, prompt) [service.py:381]
│ │
│ ├─ 步骤1:人脸检测 + 头发分割(仅 use_mask=True 时)
│ │ ├─ get_landmarker().detect(rgb) MediaPipe 478点人脸检测
│ │ │ → landmarks(无人脸返回 no_face
│ │ ├─ get_parser().parse(rgb) SegFormer 面部分割(CPU ~0.9s
│ │ │ → parse_mapint label map
│ │ │
│ ├─ 步骤2:手绘发际线检测(仅 use_mask=True 时)
│ │ ├─ detect_marker_hairline(marked_bgr, landmarks, parse_map)
│ │ │ │ [marker_detect.py:41]
│ │ │ ├─ forehead_upper_region(landmarks) 额头上部 ROI
│ │ │ ├─ head_silhouette(parse_map) 头部轮廓 ROI
│ │ │ ├─ _blackhat(gray) 黑帽变换(响应比邻域暗的细结构)
│ │ │ ├─ _snap_anchor(bh, 左鬓角21) 左锚点吸附
│ │ │ ├─ _snap_anchor(bh, 右鬓角251) 右锚点吸附
│ │ │ ├─ route_through_array(cost, 左, 右) Dijkstra最小代价路径
│ │ │ └→ path (N,2) row,col(拒识返回 None → no_line
│ │ │
│ │ ├─ path_to_curve_mask(path) 路径→曲线maskuint8 0/255
│ │ └─ mask_from_curve(curve_mask, landmarks, parse_map)
│ │ │ [mask.py]
│ │ ├─ _above_curve_region(curve_mask) 曲线以上区域
│ │ ├─ cv2.morphologyEx(闭运算) 填洞
│ │ ├─ 最大连通域
│ │ └─ 高斯羽化 → mask (uint8 0-255)
│ │
│ ├─ 步骤3:合成 RGBA PNG
│ │ ├─ compose_comfy_rgba(marked_bgr, mask) RGB=原图,alpha=255×(1-mask)
│ │ └─ PNG 编码 → rgba_png_bytes
│ │
│ └─ 步骤4ComfyUI 生发
│ └─ comfyui.run(rgba_png_bytes, prompt) [comfyui.py:87]
│ ├─ 上传图片到 ComfyUI /upload/image
│ ├─ 加载工作流 add_hair.json
│ ├─ 替换节点26输入图 + 节点6随机seed + 节点60提示词
│ ├─ POST /prompt 提交工作流
│ ├─ 轮询 /history/{prompt_id}(间隔0.2s
│ └─ GET /view 取回输出 PNG → grown_png
└─ 返回 {"grown_png": bytes, "status": "ok"}
```
---
## 四、用到的模型和外部服务
| 模型/服务 | 用途 | 位置 | 设备 |
|----------|------|------|------|
| **FaceLandmarker** (MediaPipe) | 478点人脸检测 | hairline/face_landmarks.py | CPU |
| **FaceParser** (SegFormer) | 面部分割(hair/skin/... | hairline/face_parsing.py | CPU (5090不兼容cu121) |
| **ComfyUI** (Flux-2) | 生发图生成 | hairline/comfyui.py → :8188 | GPU |
**注意**:接口3 **不调用** change_hair 服务(:8801),不需要 swapHair。这是它与接口2女性流程的关键区别。
---
## 五、核心算法:手绘发际线检测
### 5.1 为什么不用简单阈值?
手绘马克笔线条的灰度值与皮肤阴影、抬头纹等重叠,全局阈值无法区分。采用**黑帽变换 + Dijkstra最小路径**方案。
### 5.2 黑帽变换(Black Hat
```python
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (k, k))
bh = cv2.morphologyEx(gray, cv2.MORPH_BLACKHAT, kernel)
```
黑帽 = 闭运算 − 原图,响应"比局部邻域暗的细结构"(即马克笔线条),对抬头纹/眉毛/发丝鲁棒。
### 5.3 Dijkstra 最小代价路径
1. **ROI 限定**:额头上部 ∩ 头部轮廓(排除背景)
2. **锚点**:左鬓角(21) / 右鬓角(251) MediaPipe 关键点
3. **代价图**`cost = (bh.max() - bh) + 1.0`ROI外设 1e6
4. **路径**`route_through_array(cost, 左锚, 右锚)` — skimage 的 Dijkstra 实现
### 5.4 拒识机制
路径平均黑帽响应 < 8.0 → 判定"未画线",返回 `no_line`
---
## 六、与接口1、接口2 的对比
| 维度 | 接口1 | 接口2 | 接口3 |
|------|-------|-------|-------|
| 功能 | 四庭七眼测量 | C端生发(5种发际线) | B端生发(手绘线) |
| 路由 | /api/v1/face/measure | /api/v1/hair/grow | /api/v1/hair/grow-b |
| 输入 | 正面照 | 正面照 | 划线图 |
| MediaPipe | ✅ | ✅ | ✅ |
| SegFormer | ✅ | ✅ | ✅ |
| change_hair | ❌ | ✅(女性) | ❌ |
| ComfyUI | ❌ | ✅(Flux-2重绘) | ✅(Flux-2生发) |
| 典型耗时 | ~2s | ~11s | ~6-8s |
| ComfyUI工作流 | — | 0716add-hair-api.json | add_hair.json |
---
## 七、测试
- **测试页面**[static/test_interface3.html](file:///home/ubuntu/hair/static/test_interface3.html)
- **测试图片**[image/girl_img/girl13.jpg](file:///home/ubuntu/hair/image/girl_img/girl13.jpg)(需手动在图上画发际线后作为划线图上传)
@@ -1,12 +1,12 @@
# 发际线生发遮罩算法(pushed 模式)
> 对应接口11 `/api/v1/hairline/grow`、接口12 `/api/v1/hairline/grow_v2`。
> 遮罩算法固定为 pushed融合算法固定为 multiband已移除其他选项)
> 代码:`face_analysis/hairline_grow.py``_extract_hairline` / `_pushed_mask` / `compute_mask`)。
> 遮罩算法固定为 pushed融合算法默认 multiband多频段金字塔),接口11 可切换 seamless/two_stage/feather
> 代码:`face_analysis/hairline_grow.py``_extract_hairline` / `_pushed_mask` / `compute_mask` / `_composite`)。
## 概述
pushed 是发际线生发的**唯一**遮罩算法multiband(多频段金字塔)是**唯一**融合算法。它从头发分割结果中提取「头发/皮肤交界线」(发际线),以眉心为圆心逐点径向外推一段距离,与 baseline 组成闭合区域作为最终遮罩。这样遮罩顶部会覆盖现有头发下沿一小段,贴回生发结果时顶部与真头发重叠、过渡自然。
pushed 是发际线生发的**唯一**遮罩算法。融合算法默认 multiband(多频段金字塔),接口11 暴露 `blend_method` 可切换为 seamless(泊松)/two_stage(泊松→多频段两段式)/feather(羽化),便于对比调优。它从头发分割结果中提取「头发/皮肤交界线」(发际线),以眉心为圆心逐点径向外推一段距离,与 baseline 组成闭合区域作为最终遮罩。这样遮罩顶部会覆盖现有头发下沿一小段,贴回生发结果时顶部与真头发重叠、过渡自然。
> 接口12 `/api/v1/hairline/grow_v2` 只需传 `image` + `hairline_id`,遮罩和融合全部固定,无需任何算法选择参数。
@@ -57,14 +57,48 @@ segformer(默认)或 bisenet 得到的头发二值掩码。
## 关键参数
遮罩算法(pushed融合算法(multiband)已固定,接口不再暴露选择参数可调的只有
遮罩算法(pushed固定。融合算法接口11 通过 `blend_method` 可切换(默认 multiband),其余融合参数可调:
| 参数 | 默认 | 说明 |
|---|---|---|
| `hairline_push_cm` | 1.0 | 内轮廓径向外推距离(厘米),= push_px / px_per_cm。`px_per_cm` 由虹膜直径标定 |
| `hairline_edge` | `column` | 兼容保留的入参;内轮廓提取(轮廓+内侧判定)不再按它分支,取值不影响结果 |
| `mb_levels` | 5 | 多频段金字塔层数(2~6,越大低频色差抹得越宽)|
| `blend_method` | `multiband` | 接缝融合:multiband(多频段金字塔) / seamless(泊松) / two_stage(泊松→多频段,大色差) / feather(羽化) / alpha_gradient。接口12 固定 multiband |
| `color_match` | `true` | 融合前 Reinhard 颜色迁移消除整体色差(multiband/feather/alpha_gradient 生效;seamless/two_stage 自带调色故跳过)|
| `color_match_strength` | 1.0 | 颜色迁移强度(0~1<1 只迁移部分,防 Reinhard 过度改色)|
| `mb_feather_px` | 1 | 多频段最细层掩码轻羽化像素(0=不羽化),消除发丝边缘锯齿 |
| `transition_band_px` | -1 | keep-region 过渡带边距(-1=自动按层数 `2**n`;>=0 用绝对像素与层数解耦)|
| `edge_erode_px` | 3 | 贴图前遮罩内缩像素(防边缘露皮/光晕)|
| `erode_cm` | 0.6(接口12 固定)| baseline 参考内缩距离,对 pushed 影响很小 |
| `redraw` | `false` | 发际线带重绘开关:开启后用 final(④融合图)在「外推线↔发际线」带重绘,swapHair/Flux-2 两路对比,结果单独展示(不替换 final)|
| `inpainting_fill` | 1 | change_hair 重绘填充:0=保留原图(治染绿) / 1=填充噪声(默认) / 2=纯色 / 3=潜变量噪声 |
| `mask_blur` | 11 | change_hair 遮罩边缘模糊像素(越大颜色越易从边缘渗透)|
| `mask_dilate_scale` | 1.0 | change_hair 遮罩膨胀核缩放(1.0=原始,<1 收缩防越界)|
| `comfyui_prompt` | `null` | redraw Flux-2 路提示词,null 用默认「补充遮罩区域的头发,加一点美颜」|
> 接口12 `/api/v1/hairline/grow_v2` 只需传 `image` + `hairline_id`,遮罩和融合全部用默认值(multiband + color_match=true),不暴露算法选择参数。
### 融合方法选择建议
- **multiband**(默认):常规首选。低频抹色差、高频保发丝。需配合 `color_match=true` 消除整体色差。
- **two_stage**:生成图与原图色差大时用。先泊松克隆统一色调,再多频段贴细节,兼顾调色与保发丝。比纯 seamless 更不易溢色。
- **seamless**:纯泊松梯度域调和,色调统一干净,但可能整体改色/边缘溢色。
- **feather / alpha_gradient**:单层 alpha 过渡,最轻量,但过渡带内色差不会被抹平,仅适合色差极小的场景。
## 发际线带重绘(redraw,接口11 可选)
`redraw=true` 时,在主流程(④接缝融合 final)之后额外跑一条重绘分支,结果单独展示(`steps.redraw_a` / `redraw_c`),**不替换** final。
**重绘区域** = ①-g 外推发际线(`outer_pts`)与 ①-f 发际线(`inner_pts`)两条折线端点相连组成的带状闭合区域(宽度 ≈ `hairline_push_cm`,只覆盖发际线交界处)。
**两路后端对比**(输入图 + 融合基底都用 final):
- **swapHair 路**`redraw_a`):final + 带遮罩调 change_hair → final 走 multiband 融合
- **Flux-2 路**`redraw_c`):final + 带遮罩调 ComfyUI`hair_repaint.json` 工作流)→ final 走 multiband 融合。Flux-2 经 reference latent + ColorMatch 双重保色,**不易染绿**
> `inpainting_fill` / `mask_blur` / `mask_dilate_scale` 透传 change_hair 服务端(仅影响 swapHair 路)。`comfyui_prompt` 仅影响 Flux-2 路。
> 两路独立容错:任一路失败只跳过该路,不影响另一路和主 final。
> ⚠️ Flux-2 路需 ComfyUI8188)在跑;swapHair 路需 change_hair8801)在跑。
## 与旧模式(eroded/closed,已移除)的区别
+182
View File
@@ -0,0 +1,182 @@
# 接口11 运行记录 — `image/hair_test.jpg`
> 实测时间:2026-07-15
> 调用:`POST http://127.0.0.1:8187/api/v1/hairline/grow`
> 鉴权:`X-Internal-Token: dev-shared-secret-2026`
> 输入图:`image/hair_test.jpg`1257×1495
> `hairline_id``chang_zhixian`(直线);其余全部走接口默认值
> 业务结果:`code=0``rid=bc7205a4`
> 产物目录:`docs/iface11_hair_test_run/`
---
## 1. 本次调用用到的全部默认参数
未在 Form 里显式传的参数均取 `app.py` / `generate_hairline_grow` 默认值;下表即本次实际生效值。
| 参数 | 本次值 | 说明 |
|------|--------|------|
| `hairline_id` | `chang_zhixian` | **必填**。发际线类型 = change_hair 的 `hair_id`(直线) |
| `gen_backend` | `swaphair` | 生成后端:换发型 LoRA |
| `hairgrow_strength` | `0.75` | 仅 `hairgrow` 后端用;本次未走该路径 |
| `is_hr` | `false` | 高清关闭(576×768 档,非 1152×1536 |
| `seg_model` | `segformer` | 头发分割模型 |
| `erode_cm` | `0.6` | baseline 参考内缩(cm);pushed 下影响很小 |
| `hairline_push_cm` | `1.0` | 发际线内轮廓径向外推距离(cm) |
| `hairline_edge` | `column` | 兼容入参;当前内轮廓提取不再按它分支 |
| `swap_mode` | `ext_mask` | 把 pushed 遮罩作为 `ext_mask` 传给 swapHair |
| `edge_erode_px` | `3` | 贴图前遮罩内缩像素 |
| `denoising_strength` | `0.6` | 换发型 webui 重绘强度 |
| `mb_levels` | `5` | 多频段金字塔层数 |
| `blend_method` | `multiband` | 接缝融合:多频段金字塔 |
| `color_match` | `true` | 融合前 Reinhard 颜色迁移 |
| `color_match_strength` | `1.0` | 颜色迁移强度(全迁移) |
| `mb_feather_px` | `1` | 多频段最细层掩码轻羽化 |
| `transition_band_px` | `-1` | keep-region 过渡带:自动按层数 `2**n` |
| `redraw` | `false` | 发际线带重绘关闭 |
| `inpainting_fill` | `1` | change_hair 填充噪声 |
| `mask_blur` | `11` | change_hair 遮罩边缘模糊像素 |
| `mask_dilate_scale` | `1.0` | change_hair 遮罩膨胀缩放 |
| `comfyui_prompt` | `null` | 仅 `redraw`+Flux-2 路用;本次未用 |
| `mask_type` | `pushed`(固定) | 代码写死,不可选 |
图片入参:仅传了 `image_file`(三选一中的文件上传)。
---
## 2. 返回元数据(无 base64
| 字段 | 值 |
|------|-----|
| `px_per_cm` | 47.5311(虹膜直径标定) |
| `erode_px` | 29(≈ 0.6cm × px_per_cm |
| `hair_pixels` | 186798 |
| `closed_pixels` | 191712 |
| `mask_pixels` | 140299 |
| `image_size` | 1257 × 1495 |
| `timings_ms.mask` | 1462 |
| `timings_ms.swap` | 5596 |
| `timings_ms.blend` | 220 |
| `redraw.enabled` | false |
| 总耗时(curl | ≈ 7.4 s |
完整精简 JSON`docs/iface11_hair_test_run/response_meta.json`
完整原始响应(含 base64):`docs/iface11_hair_test_run/response.json`
---
## 3. 管线分步说明与产物
管线:① pushed 遮罩 → ② swapHair 生成 → ③ 硬贴回 → ④ multiband 融合。
各步图保存在 `docs/iface11_hair_test_run/steps/`
### ①-a 发际线分割线(baseline
- **做什么**:MediaPipe 关键点连成眉骨折线(中心为 151 眉心),并向左右边缘水平延长。
- **图**[`steps/baseline_overlay.jpg`](iface11_hair_test_run/steps/baseline_overlay.jpg)
- **含义**:黄线 = baseline;151 中心点为后续径向外推圆心。
### ①-b 分割线上半区(upper
- **做什么**:baseline 折线以上的多边形区域,作为后续裁剪范围。
- **图**[`steps/upper_overlay.jpg`](iface11_hair_test_run/steps/upper_overlay.jpg)
- **含义**:青 = 上半区。
### ①-c 头发分割(hair_seg
- **做什么**:SegFormer 得到头发二值掩码。
- **图**[`steps/hair_seg_overlay.jpg`](iface11_hair_test_run/steps/hair_seg_overlay.jpg)
- **含义**:绿 = 原始头发像素(本次 `hair_pixels=186798`)。
### ①-d / ①-e(旧 eroded/closed 中间步)
- pushed 模式**不走**这两步;返回字段为空字符串。
- `top_fill_overlay` / `closed_overlay`:本次无图。
### ①-f 头发内轮廓线(hairline
- **做什么**:取头发朝脸一侧的内轮廓(额头弧 + 两侧到下颌),有序折线。
- **图**[`steps/hairline_overlay.jpg`](iface11_hair_test_run/steps/hairline_overlay.jpg)
- **含义**:绿 = 内轮廓;黄 = baseline。
### ①-g 外推发际线(pushed
- **做什么**:以眉心 151 为圆心,内轮廓逐点向外推 `hairline_push_cm=1.0`(≈ 47.5 px),与 baseline 组闭合区域。
- **图**[`steps/pushed_overlay.jpg`](iface11_hair_test_run/steps/pushed_overlay.jpg)
- **含义**:青 = 外推线;红 = 外推遮罩区域。
### ① 最终遮罩
- **叠加图**[`steps/mask_overlay.jpg`](iface11_hair_test_run/steps/mask_overlay.jpg) — 红 = 遮罩区(贴回/生成区)
- **纯遮罩**[`steps/mask.png`](iface11_hair_test_run/steps/mask.png) — 白 = 生成/贴回区
- 本次 `mask_pixels=140299`;贴图前再内缩 `edge_erode_px=3`
### ② 生成全帧(swap_raw
- **做什么**`gen_backend=swaphair` + `swap_mode=ext_mask`,把遮罩交给 change_hair`:8801`),LoRA=`chang_zhixian``denoising_strength=0.6`
- **图**[`steps/swap_raw.jpg`](iface11_hair_test_run/steps/swap_raw.jpg)
- **含义**:生成结果已与原图同分辨率对齐;耗时约 5.6 s。
### ③ 严格按遮罩贴回(hard_paste
- **做什么**:遮罩内用生成图,遮罩外保持原图,无融合。
- **图**[`steps/hard_paste.jpg`](iface11_hair_test_run/steps/hard_paste.jpg)
- **含义**:用于对比接缝融合前后差异。
### ④ 融合权重 alpha + 最终结果
- **做法**`blend_method=multiband``mb_levels=5``color_match=true`(强度 1.0),`mb_feather_px=1`
- **alpha**[`steps/alpha.png`](iface11_hair_test_run/steps/alpha.png) — 白 = 更多采用生成图
- **最终输出**[`steps/final.jpg`](iface11_hair_test_run/steps/final.jpg)(副本:[`final.jpg`](iface11_hair_test_run/final.jpg)
- **输入对照**[`steps/input.jpg`](iface11_hair_test_run/steps/input.jpg)
### ⑤ 发际线带重绘(本次关闭)
`redraw=false`,故 `redraw_band_overlay` / `redraw_a` / `redraw_c` 均为空。
---
## 4. 最终输出
**主结果文件**[`docs/iface11_hair_test_run/final.jpg`](iface11_hair_test_run/final.jpg)
含义:同一人、同一发型观感下,按直线发际线类型(`chang_zhixian`)压低发际线后的合成图;遮罩外像素保持原图不动。
---
## 5. 复现命令
```bash
curl -sS -X POST "http://127.0.0.1:8187/api/v1/hairline/grow" \
-H "X-Internal-Token: dev-shared-secret-2026" \
-F "image_file=@image/hair_test.jpg" \
-F "hairline_id=chang_zhixian" \
-o docs/iface11_hair_test_run/response.json
```
(其余参数全部省略即可走默认值。)
---
## 6. 产物清单
```
docs/接口11_hair_test运行记录.md ← 本文档
docs/iface11_hair_test_run/
final.jpg ← 最终结果
response.json ← 完整 API 响应(含 base64
response_meta.json ← 去掉大图的元数据
steps/
input.jpg
baseline_overlay.jpg
upper_overlay.jpg
hair_seg_overlay.jpg
hairline_overlay.jpg
pushed_overlay.jpg
mask_overlay.jpg
mask.png
swap_raw.jpg
hard_paste.jpg
alpha.png
final.jpg
```
+34 -68
View File
@@ -20,7 +20,6 @@
| 3 B 端生发 | POST | `/api/v1/hair/grow-b` |
| 4 用户特征 | POST | `/api/v1/face/features` |
| 5 发际线 PNG 生成 | POST | `/api/v1/hairline/generate` |
| 7 C 端生发 v2 | POST | `/api/v1/hair/grow-v2` |
---
@@ -87,6 +86,7 @@
| 1006 | 文件超出大小限制 | 单文件超过 1 MB |
| 1007 | 图片参数错误 | file / url / base64 未传,或同时传了多个(三者严格互斥) |
| 1008 | 图片格式不支持 | 非 JPG / PNG |
| 1009 | 未授权 | 缺少或错误的 `X-Internal-Token``/api/*` 路径鉴权) |
---
@@ -109,6 +109,8 @@
| four_courts | object | 四庭数据,见下表 |
| seven_eyes | object | 七眼数据,见下表 |
| landmarks | object | 关键分界点坐标(头顶 / 发际线 / 眉心 / 鼻翼下缘 / 下巴尖),原图像素坐标 |
| left_position | object | MediaPipe 21 号关键点坐标(左脸定位点),原图像素:`{ "x": int, "y": int }` |
| right_position | object | MediaPipe 251 号关键点坐标(右脸定位点,与 21 号镜像),原图像素:`{ "x": int, "y": int }` |
`four_courts`(四庭,自上而下):
@@ -209,8 +211,12 @@
| annotated_image_url | string | 标注图层 PNG URL(透明底,仅标注线/文字,不含人物) |
| face_total_height_cm | number | 面部总高度(cm)= 上庭 + 中庭 + 下庭(**不含顶庭**) |
| four_courts | object | 三庭数据(上/中/下庭,各含 cm 与 ratio**无顶庭** |
| seven_eyes | object | 七眼数据(眼宽/脸宽/两眼间距,各含 cm ratio |
| seven_eyes | object | 七眼数据(眼宽/脸宽/两眼间距 cm + 占比 ratios + **eye2~eye6** 共 5 段宽度 |
| landmarks | object | 四个关键点像素坐标(发际线/眉心/鼻翼下缘/下巴尖) |
| left_position | object | MediaPipe 21 号关键点坐标(左脸定位点),原图像素:`{ "x": int, "y": int }` |
| right_position | object | MediaPipe 251 号关键点坐标(右脸定位点,与 21 号镜像),原图像素:`{ "x": int, "y": int }` |
> 接口6 是**三庭五眼**`four_courts`/`landmarks` 不含顶庭与头顶点(无 `top_court_cm`/`hair_top`);`seven_eyes` 只含 **eye2~eye6**(左脸颊/左眼/两眼间距/右眼/右脸颊,5 段),**无 eye1/eye7**(耳外段需头发轮廓端线,仅接口1 有)。
### 响应示例
@@ -228,7 +234,8 @@
},
"seven_eyes": {
"eye_width_cm": 3.44, "face_width_cm": 24.08, "inter_eye_distance_cm": 3.44,
"ratios": { "eye_width": 0.143, "inter_eye_distance": 0.143 }
"ratios": { "eye_width": 0.143, "inter_eye_distance": 0.143 },
"eye2": 3.0, "eye3": 3.44, "eye4": 3.44, "eye5": 3.44, "eye6": 3.0
},
"landmarks": {
"hairline": { "x": 540, "y": 430 },
@@ -244,10 +251,10 @@
## 接口 2C 端生发接口
**说明**:输入用户正面照 + 性别 + 发型序号(可多选),按指定发际线类型渲染预览图 + 生发图。
**说明**:输入用户正面照 + 性别 + 发型序号(可多选),按指定发际线类型渲染发际线曲线透明 PNG + 生发图。
> **每个方案返回两张图**`image_url`=「原照片 + 发际线曲线叠加的**预览图**」;`grown_image_url`=
> 经 ComfyUI/Flux 的「植发 3 个月**生发后图片**」。两者均已实现,实现简述见 [`实现说明.md`](实现说明.md)。
> **每个方案返回两张图**`image_url`=「发际线曲线**透明 PNG**(仅白色曲线,透明底,需叠加原图显示)」;`grown_image_url`=
> 经 ComfyUI/Flux 的「植发 3 个月**生发后图片**」(完整人像照片)。两者均已实现,实现简述见 [`实现说明.md`](实现说明.md)。
**请求**`POST /api/v1/hair/grow`
@@ -261,6 +268,7 @@
| hair_style | string | **是** | 发型序号,**逗号分隔多选**(如 `1,2,3`),最多不超过该性别的预设数。female1=ellipse, 2=flower, 3=heart, 4=straight, 5=wavemale1=ellipse, 2=inverse_arc, 3=m, 4=straight。越界/非法返回 `1007` |
| beauty_enabled | bool | 否 | 生发图是否带美颜效果,默认 false(当前阶段不生效) |
| use_mask | bool | 否 | 是否启用 inpaint 遮罩,默认 `true``false` 时用干净原图生成(空遮罩、不烧模板黑线),供测试对比 |
| prompt | string | 否 | ComfyUI 提示词,默认「补充遮罩区域的头发,加一点美颜」,会替换工作流节点 60 的文本 |
### 输出(data
@@ -268,14 +276,16 @@
| 字段 | 类型 | 说明 |
|------|------|------|
| image_url | string | 方案**预览图** URL(发际线曲线叠加图 |
| grown_image_url | string | **生发后图片** URLComfyUI/Flux「植发 3 个月」效果图) |
| image_url | string | 发际线曲线**透明 PNG** URL仅白色发际线曲线,透明底,**不含人物**,需前端叠加原图显示 |
| grown_image_url | string | **生发后图片** URLComfyUI/Flux「植发 3 个月」效果图,完整人像照片 |
| hairline_type | string | 发际线类型 key`ellipse`/`flower`/`heart`/`straight`/`wave`female),`ellipse`/`m`/`straight`/`inverse_arc`male |
| order | int | 排序序号(当前阶段固定 `1..N`,按贴图顺序,暂不计算合适度) |
> ⚠️ 生发图由本机 ComfyUIFlux-2,端口 8182)生成,**一次请求生成指定发型的 1 张、同步返回**。
> worker 侧返回 `image_base64` / `grown_image_base64`
> 网关落盘后改写为上表的 `image_url` / `grown_image_url`。
>
> 💡 `image_url` 为透明底 PNG,前端需用绝对定位叠加到原图上显示(参考[测试页](https://hair.xiangsilian.com/static/test_interface2.html)的 `.img-stack` 叠加结构)。
### 响应示例
@@ -313,6 +323,7 @@
|------|------|------|------|
| marked_image_* | file / string | 是 | 已用马克笔标注发际线的图片,三选一 |
| use_mask | bool | 否 | 是否画发际线,默认 `true``false` 时跳过划线检测、直接送划线图,模型仅凭手绘黑线生发,供测试对比 |
| prompt | string | 否 | ComfyUI 提示词,默认「补充遮罩区域的头发,加一点美颜」,会替换工作流节点 60 的文本 |
### 输出(data
@@ -397,7 +408,8 @@
| gender | string | **是** | 性别:`male` / `female`。决定发型集合(female 5 / male 4)。缺失/非法返回 `1004` |
| hair_style | string | **是** | 发型序号,**逗号分隔多选**(如 `1,2,3`),决定返回哪些发际线类型。female1=ellipse, 2=flower, 3=heart, 4=straight, 5=wavemale1=ellipse, 2=inverse_arc, 3=m, 4=straight。缺失/越界/非法返回 `1007` |
| use_mask | bool | 否 | 生发是否启用 inpaint 遮罩,默认 `true``false` 时用干净原图生成(空遮罩、不烧模板黑线),供测试对比 |
| prompt | string | 否 | ComfyUI 提示词,默认「补充遮罩区域的头发」,会替换工作流节点 60 的文本 |
| prompt | string | 否 | ComfyUI 提示词,默认「补充遮罩区域的头发,加一点美颜」,会替换工作流节点 60 的文本 |
| generate_grow_image | bool | 否 | 是否生成生发效果图(ComfyUI 生发,全流程最耗时),默认 `true`。传 `false` 时跳过生发,各发型 `grown_image_*` 恒为 `null`,仅返回三档发际线叠图与中心点,可大幅降低耗时 |
> ⚠️ 三档叠图分别用 `hairline_texture` / `hairline_texture_high` / `hairline_texture_low` 三套同名贴图;**生发黑模板固定取自 `hairline_texture_black/`middle 档)**,即生发目标固定压到 middle 档,每个发型仅 1 张生发图。
@@ -406,7 +418,9 @@
| 字段 | 类型 | 说明 |
|------|------|------|
| hairline_images | object[] | **选中发型**列表,**数量 = 所选发型数**,元素见下表 |
| best_hairline_center_point | object | **首个选中发型**的 middle 档发际线曲线「面部中间点」坐标,原图像素:`{ "x": number, "y": number }` |
| best_hairline_center_point | object \| null | **首个选中发型**的 **middle 档**发际线曲线「面部中间点」坐标,原图像素:`{ "x": number, "y": number }` |
| high_hairline_center_point | object \| null | 同上,**high 档**发际线中点(发际线偏高) |
| low_hairline_center_point | object \| null | 同上,**low 档**发际线中点(发际线偏低) |
| face_measure | object \| null | **复用接口1**的四庭七眼测量**数值**(不含标注图)。独立流程,测量失败(无人脸/非正面/分割失败)时为 `null`,不影响发际线主结果。字段结构见下表 |
`hairline_images` 元素:
@@ -414,13 +428,15 @@
| 字段 | 类型 | 说明 |
|------|------|------|
| hairline_type | string | 发际线类型 key`ellipse`/`flower`/`heart`/`straight`/`wave`female),`ellipse`/`m`/`straight`/`inverse_arc`male |
| image_middle_url | string | middle 档发际线叠加图 URL |
| image_high_url | string | high 档发际线叠加图 URL |
| image_low_url | string | low 档发际线叠加图 URL |
| grown_image_url | string \| null | **生发后图片** URLComfyUI「植发」效果图,生发失败时为 `null` |
| image_middle_url | string | middle 档发际线曲线**透明 PNG** URL(仅曲线,透明底,**不含人物**,需叠加原图显示) |
| image_high_url | string | high 档发际线曲线**透明 PNG** URL(同上,high 档曲线) |
| image_low_url | string | low 档发际线曲线**透明 PNG** URL(同上,low 档曲线) |
| grown_image_url | string \| null | **生发后图片** URLComfyUI「植发」效果图,完整人像照片,生发失败或 `generate_grow_image=false` 时为 `null` |
| order | int | 发型序号(= 传入的 hair_style 值) |
> worker 侧返回 `image_middle_base64` / `image_high_base64` / `image_low_base64` / `grown_image_base64`,网关落盘后改写为上表对应的 `*_url`。
>
> 💡 三档 `image_*_url` 为透明底 PNG,前端需用绝对定位叠加到原图上显示(参考[测试页](https://hair.xiangsilian.com/static/test_interface5.html)的 `.img-stack` 叠加结构)。`grown_image_url` 是完整人像照片,直接显示即可。
`face_measure` 元素(与[接口1](#接口-1四庭七眼测量标注接口)的 `data` 同构,**不含** `annotated_image_*` 标注图字段):
@@ -432,6 +448,8 @@
| landmarks | object | 5 个纵向关键点像素坐标(hair_top/hairline/brow_center/nose_bottom/chin_tip),结构同接口1 |
| hairline_source | string | 发际线来源:`segmentation`(真实分割)/ `estimated`(比例估算) |
| head_pose | object | 头部姿态角度(yaw/pitch/roll,单位:度) |
| left_position | object | MediaPipe 21 号关键点坐标(左脸定位点),原图像素:`{ "x": int, "y": int }` |
| right_position | object | MediaPipe 251 号关键点坐标(右脸定位点,与 21 号镜像),原图像素:`{ "x": int, "y": int }` |
> `eye1`~`eye7` 为从左到右共 7 段宽度,eye1=左耳外段、eye7=右耳外段,某侧耳朵不可见时对应段为 `null`。详见接口1说明。
@@ -462,6 +480,8 @@
}
],
"best_hairline_center_point": { "x": 540, "y": 430 },
"high_hairline_center_point": { "x": 540, "y": 380 },
"low_hairline_center_point": { "x": 540, "y": 480 },
"face_measure": {
"face_total_height_cm": 26.76,
"four_courts": {
@@ -495,59 +515,6 @@
---
## 接口 7:C 端生发 v2 接口
**说明**:功能与[接口 2](#接口-2c-端生发接口)完全一致,仅 ComfyUI 工作流不同——使用 `add_hair2.json` 替代 `add_hair.json`
**请求**`POST /api/v1/hair/grow-v2`
### 输入
与接口 2 完全相同。图片参数见「通用约定 → 图片传参字段」。专属参数:
| 参数 | 类型 | 必填 | 说明 |
|------|------|------|------|
| gender | string | **是** | 性别:`male` / `female`。决定使用的发际线贴图集合 |
| hair_style | string | **是** | 发型序号,**逗号分隔多选**(如 `1,2,3`)。female1=ellipse, 2=flower, 3=heart, 4=straight, 5=wavemale1=ellipse, 2=inverse_arc, 3=m, 4=straight。越界/非法返回 `1007` |
| beauty_enabled | bool | 否 | 生发图是否带美颜效果,默认 false(当前阶段不生效) |
| use_mask | bool | 否 | 是否启用 inpaint 遮罩,默认 `true``false` 时用干净原图生成(空遮罩、不烧模板黑线) |
### 输出(data
与接口 2 完全相同。`results`:发际线方案数组,**数量 = 所选发型数**。每个元素:
| 字段 | 类型 | 说明 |
|------|------|------|
| image_url | string | 方案**预览图** URL(发际线曲线叠加图) |
| grown_image_url | string | **生发后图片** URLComfyUI/Flux「植发 3 个月」效果图) |
| hairline_type | string | 发际线类型 key |
| order | int | 排序序号 |
> ⚠️ 与接口 2 的区别:本接口使用 `add_hair2.json` 工作流(Flux-2 Klein 9b),输入/遮罩节点同为 26,
> SaveImage 输出节点为 75。
### 响应示例
```json
{
"code": 0,
"message": "success",
"request_id": "mock-request-id",
"data": {
"results": [
{
"image_url": "https://hair.xiangsilian.com/static/sample.jpg",
"grown_image_url": "https://hair.xiangsilian.com/static/sample.jpg",
"hairline_type": "ellipse",
"order": 1
}
]
}
}
```
---
## 汇总:输入输出一览
| 接口 | 输入 | 主要输出 |
@@ -558,7 +525,6 @@
| 3 B 端生发 | 划线图片 | 最合适发际线图片 + 生发后图片 |
| 4 用户特征 | 用户照片 | 6 个用户特征字段(脸形/眉形/年龄/动静/性别/基因风格) |
| 5 发际线 PNG | 用户照片 + gender + hair_style(多选) | 每个选中发型 middle/high/low 三档发际线叠图 + 生发图 + 最合适发际线面部中间点坐标 |
| 7 C 端生发 v2 | 用户照片 + gender + hair_style | 同接口2,使用 add_hair2.json 工作流 |
---
+506
View File
@@ -0,0 +1,506 @@
"""
build_dataset_report.py
对任意图片目录(可含多层子目录)批量预测脸型并生成 HTML 报告。
保留图片原始所属的子目录名作为「分组」,在报告中按分组展示与统计。
用法:
./venv/bin/python face/build_dataset_report.py --src <图片目录> [--sample 50] [--seed 42]
示例:
./venv/bin/python face/build_dataset_report.py \
--src face/test_img/脸型测试集合 --sample 50 --name 脸型测试集合
输出:
static/<slug>_report.html
static/<slug>_report/images/*.jpg
"""
from __future__ import annotations
import argparse
import html
import random
import re
import shutil
import sys
import unicodedata
from collections import Counter, defaultdict
from datetime import datetime
from pathlib import Path
from typing import Dict, List
import cv2
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
from face.face_shape_classifier import classify_from_image # noqa: E402
ROOT = Path(__file__).resolve().parents[1]
IMAGE_SUFFIXES = {".jpg", ".jpeg", ".png", ".webp", ".bmp"}
MAX_IMAGE_SIDE = 900
JPEG_QUALITY = 88
SHAPE_ORDER = ["圆形脸", "心形脸", "菱形脸", "鹅蛋脸", "方形脸", "长形脸", "瓜子脸"]
SHAPE_COLORS = {
"圆形脸": "#e67e22",
"心形脸": "#e74c3c",
"菱形脸": "#9b59b6",
"鹅蛋脸": "#27ae60",
"方形脸": "#2980b9",
"长形脸": "#16a085",
"瓜子脸": "#c0392b",
"检测失败": "#7f8c8d",
}
# 数据集分组名与分类器脸型口径的近似对应(仅用于交叉表高亮参考,非严格标签)
TAXONOMY_EQUIV = {
"方形脸": "方形脸",
"长形脸": "长形脸",
"瓜子脸": "瓜子脸",
"标准脸": "鹅蛋脸",
"娃娃脸": "圆形脸",
}
FEATURE_KEYS = [
"face_width",
"face_height",
"jaw_angle",
"taper_ratio",
"forehead_ratio",
"cheekbone_ratio",
"jaw_ratio",
"chin_ratio",
"chin_sharpness",
"width_uniformity",
"face_curve_score",
]
def natural_key(text: str):
parts = re.split(r"(\d+)", text)
return [int(p) if p.isdigit() else p for p in parts]
def collect_images(src: Path) -> List[Path]:
return sorted(
(p for p in src.rglob("*") if p.suffix.lower() in IMAGE_SUFFIXES),
key=lambda p: natural_key(str(p.relative_to(src))),
)
def group_of(path: Path, src: Path) -> str:
"""图片相对根目录的父目录名;直接位于根目录则记为「根目录」。"""
rel = path.relative_to(src).parent
return str(rel) if str(rel) != "." else "(根目录)"
def ascii_slug(text: str, fallback: str) -> str:
"""生成安全的 ASCII 文件名片段(中文目录名转拼音不可靠,直接编号兜底)。"""
norm = unicodedata.normalize("NFKD", text).encode("ascii", "ignore").decode()
norm = re.sub(r"[^A-Za-z0-9_-]+", "_", norm).strip("_")
return norm or fallback
def stratified_sample(
images: List[Path], src: Path, total: int, seed: int, min_per_group: int
) -> List[Path]:
"""
按分组分层抽样:先保证每组至少 min_per_group 张,剩余名额按组大小比例分配。
小分组(如只有 3 张的梨形脸)在纯随机抽样下几乎必然缺席,分层可保证覆盖。
"""
rng = random.Random(seed)
buckets: Dict[str, List[Path]] = defaultdict(list)
for p in images:
buckets[group_of(p, src)].append(p)
groups = sorted(buckets, key=natural_key)
quota = {g: min(min_per_group, len(buckets[g])) for g in groups}
remaining = total - sum(quota.values())
if remaining > 0:
spare = {g: len(buckets[g]) - quota[g] for g in groups}
pool = sum(spare.values())
if pool > 0:
# 按剩余可选量比例分配,再把取整误差补给最大的分组
extra = {g: int(remaining * spare[g] / pool) for g in groups}
for g in sorted(groups, key=lambda g: -spare[g]):
if sum(extra.values()) >= remaining:
break
if extra[g] < spare[g]:
extra[g] += 1
for g in groups:
quota[g] += min(extra[g], spare[g])
chosen: List[Path] = []
for g in groups:
chosen.extend(rng.sample(buckets[g], min(quota[g], len(buckets[g]))))
return chosen
def analyze(
src: Path, sample: int, seed: int, img_dir: Path, min_per_group: int
) -> List[Dict]:
all_images = collect_images(src)
if not all_images:
raise SystemExit(f"目录中没有图片: {src}")
if sample and sample < len(all_images):
if min_per_group > 0:
chosen = stratified_sample(all_images, src, sample, seed, min_per_group)
else:
chosen = random.Random(seed).sample(all_images, sample)
chosen.sort(key=lambda p: natural_key(str(p.relative_to(src))))
else:
chosen = all_images
mode = f"分层抽样,每组至少 {min_per_group}" if min_per_group > 0 else "纯随机抽样"
print(f"共发现 {len(all_images)} 张图片,本次测试 {len(chosen)} 张({mode}seed={seed}\n")
if img_dir.exists():
shutil.rmtree(img_dir)
img_dir.mkdir(parents=True)
group_slugs: Dict[str, str] = {}
rows: List[Dict] = []
for idx, path in enumerate(chosen, 1):
group = group_of(path, src)
if group not in group_slugs:
group_slugs[group] = ascii_slug(group, f"g{len(group_slugs) + 1}")
out_name = f"{group_slugs[group]}_{idx:03d}.jpg"
item = {
"index": idx,
"group": group,
"file": path.name,
"rel_path": str(path.relative_to(src)),
# 相对 static/ 的路径(报告 HTML 也放在 static/ 根下)
"img_src": f"{img_dir.relative_to(ROOT / 'static').as_posix()}/{out_name}",
"ok": False,
"predicted": None,
"display": None,
"confidence": None,
"score": None,
"top3": [],
"features": {},
"error": None,
}
try:
result = classify_from_image(path, return_details=True, return_annotated=True)
annotated = result["annotated"]
h, w = annotated.shape[:2]
if max(h, w) > MAX_IMAGE_SIDE:
scale = MAX_IMAGE_SIDE / max(h, w)
annotated = cv2.resize(
annotated, (int(w * scale), int(h * scale)), interpolation=cv2.INTER_AREA
)
cv2.imwrite(str(img_dir / out_name), annotated, [int(cv2.IMWRITE_JPEG_QUALITY), JPEG_QUALITY])
item.update(
{
"ok": True,
"predicted": result["face_shape"],
"display": result["display"],
"confidence": result["confidence"],
"score": result["details"]["ranked"][0][1],
"top3": result["details"]["ranked"][:3],
"features": {k: result["features"][k] for k in FEATURE_KEYS},
}
)
except Exception as exc: # noqa: BLE001 - 报告需要汇总所有失败样本
img = cv2.imread(str(path))
if img is not None:
h, w = img.shape[:2]
if max(h, w) > MAX_IMAGE_SIDE:
scale = MAX_IMAGE_SIDE / max(h, w)
img = cv2.resize(img, (int(w * scale), int(h * scale)), interpolation=cv2.INTER_AREA)
cv2.imwrite(str(img_dir / out_name), img, [int(cv2.IMWRITE_JPEG_QUALITY), JPEG_QUALITY])
item["error"] = str(exc)
rows.append(item)
print(f"[{idx:3d}/{len(chosen)}] [{group}] {path.name} -> {item['display'] or 'ERR: ' + str(item['error'])}")
return rows
def bar_chart(counter: Counter) -> str:
if not counter:
return "<p class='muted'>无数据</p>"
total = sum(counter.values())
parts = []
order = [s for s in SHAPE_ORDER if counter.get(s)] + [
s for s in counter if s not in SHAPE_ORDER
]
for shape in order:
n = counter[shape]
color = SHAPE_COLORS.get(shape, "#7f8c8d")
pct = n / total * 100
parts.append(
f"<div class='bar-row'><span class='bar-label'>{html.escape(shape)}</span>"
f"<div class='bar-track'><div class='bar-fill' style='width:{pct:.1f}%;background:{color}'></div></div>"
f"<span class='bar-num'>{n}{pct:.0f}%</span></div>"
)
return "".join(parts)
def fmt_feat(key: str, value: float) -> str:
if key in {"face_width", "face_height"}:
return f"{value:.1f}px"
if key == "jaw_angle":
return f"{value:.1f}°"
return f"{value:.3f}"
def card(item: Dict) -> str:
group_tag = f"<span class='group-tag'>{html.escape(item['group'])}</span>"
if not item["ok"]:
return f"""
<article class="card error">
<a class="img-link" href="{html.escape(item['img_src'])}" target="_blank">
<img src="{html.escape(item['img_src'])}" alt="{html.escape(item['file'])}" loading="lazy"/>
</a>
<div class="body">
<div class="meta"><h3>{html.escape(item['file'])}</h3>{group_tag}</div>
<p class="badge bad">检测失败</p>
<p class="muted">{html.escape(item['error'] or '')}</p>
</div>
</article>"""
color = SHAPE_COLORS.get(item["predicted"], "#34495e")
top3 = "".join(
f"<li><span>{html.escape(name)}</span><b>{score:.1f}</b></li>" for name, score in item["top3"]
)
feat_html = "".join(
f"<tr><td>{html.escape(k)}</td><td>{html.escape(fmt_feat(k, v))}</td></tr>"
for k, v in item["features"].items()
)
return f"""
<article class="card">
<a class="img-link" href="{html.escape(item['img_src'])}" target="_blank" title="点击查看大图标注">
<img src="{html.escape(item['img_src'])}" alt="{html.escape(item['file'])}" loading="lazy"/>
</a>
<div class="body">
<div class="meta"><h3>{html.escape(item['file'])}</h3>{group_tag}</div>
<p class="path muted">{html.escape(item['rel_path'])}</p>
<p class="badge" style="background:{color}">{html.escape(item['display'])}</p>
<p class="conf">匹配度 {item['score']:.1f} · 置信度 {item['confidence']:.3f}</p>
<ul class="scores">{top3}</ul>
<details>
<summary>标注特征数值</summary>
<table>{feat_html}</table>
</details>
</div>
</article>"""
CSS = """
:root { --bg:#f3efe6; --ink:#1c1915; --muted:#6b645a; --card:#fffdf8; --line:#e2d8c8; --accent:#0f6b5c; }
* { box-sizing: border-box; }
body {
margin:0; font-family:"PingFang SC","Noto Sans SC","Segoe UI",sans-serif; color:var(--ink);
background: radial-gradient(1200px 600px at 10% -10%, #ffe8c8 0%, transparent 55%),
radial-gradient(900px 500px at 100% 0%, #d9f2ea 0%, transparent 50%), var(--bg);
}
header { padding:40px 24px 20px; max-width:1320px; margin:0 auto; }
header h1 { margin:0 0 8px; font-size:clamp(1.8rem,3vw,2.4rem); }
header p { margin:4px 0; color:var(--muted); }
.legend-box { max-width:1320px; margin:0 auto 20px; padding:0 24px; }
.legend-box .inner { background:var(--card); border:1px solid var(--line); border-radius:14px;
padding:14px 16px; font-size:.9rem; line-height:1.55; }
.legend-box code { background:#efe7da; padding:1px 6px; border-radius:4px; font-size:.84rem; }
.swatch { display:inline-block; width:10px; height:10px; border-radius:2px; margin-right:4px; vertical-align:middle; }
.stats { display:grid; grid-template-columns:repeat(auto-fit,minmax(280px,1fr)); gap:16px;
max-width:1320px; margin:0 auto 28px; padding:0 24px; }
.stat { background:var(--card); border:1px solid var(--line); border-radius:16px; padding:16px 18px; }
.stat h2 { margin:0 0 12px; font-size:1rem; }
.bar-row { display:grid; grid-template-columns:72px 1fr 80px; gap:8px; align-items:center; margin:6px 0; font-size:.86rem; }
.bar-track { height:8px; background:#efe7da; border-radius:999px; overflow:hidden; }
.bar-fill { height:100%; border-radius:999px; }
.bar-num { color:var(--muted); text-align:right; }
section { max-width:1320px; margin:0 auto 36px; padding:0 24px; }
section h2 { margin:0 0 14px; font-size:1.3rem; border-left:4px solid var(--accent); padding-left:10px; }
section h2 small { color:var(--muted); font-weight:400; font-size:.8rem; margin-left:8px; }
.grid { display:grid; grid-template-columns:repeat(auto-fill,minmax(270px,1fr)); gap:16px; }
.card { background:var(--card); border:1px solid var(--line); border-radius:18px; overflow:hidden;
display:flex; flex-direction:column; box-shadow:0 8px 24px rgba(60,40,10,.05); }
.card.error { opacity:.9; }
.img-link { display:block; }
.card img { width:100%; aspect-ratio:3/4; object-fit:cover; background:#ddd; display:block; }
.card .body { padding:14px; }
.meta { display:flex; justify-content:space-between; align-items:baseline; gap:8px; }
.meta h3 { margin:0; font-size:.95rem; word-break:break-all; }
.group-tag { font-size:.72rem; color:var(--accent); background:#e7f6f2; padding:2px 8px;
border-radius:999px; white-space:nowrap; }
.path { font-size:.72rem; margin:4px 0 0; word-break:break-all; }
.badge { display:inline-block; margin:10px 0 4px; color:#fff; padding:6px 10px; border-radius:999px;
font-weight:600; font-size:.92rem; }
.badge.bad { background:#c0392b; }
.conf { margin:0 0 8px; color:var(--muted); font-size:.85rem; }
.scores { list-style:none; padding:0; margin:0 0 8px; }
.scores li { display:flex; justify-content:space-between; padding:4px 0; border-bottom:1px dashed var(--line); font-size:.86rem; }
details { margin-top:8px; }
summary { cursor:pointer; color:var(--accent); font-size:.86rem; }
table { width:100%; border-collapse:collapse; margin-top:8px; font-size:.8rem; }
td { padding:3px 0; border-bottom:1px solid var(--line); }
td:last-child { text-align:right; font-variant-numeric:tabular-nums; }
.muted { color:var(--muted); }
.cross-wrap { overflow-x:auto; background:var(--card); border:1px solid var(--line);
border-radius:16px; padding:14px 16px; }
table.cross { border-collapse:collapse; width:100%; font-size:.88rem; }
table.cross th, table.cross td { padding:7px 10px; text-align:center; border-bottom:1px solid var(--line);
white-space:nowrap; }
table.cross thead th { background:#efe7da; font-weight:600; position:sticky; top:0; }
table.cross th.rowh { text-align:left; font-weight:600; }
table.cross th.rowh small { color:var(--muted); font-weight:400; }
table.cross td.num { font-variant-numeric:tabular-nums; }
table.cross td.hit { background:#d8f3e4; color:#0f6b5c; font-weight:700; font-variant-numeric:tabular-nums; }
table.cross td.zero { color:#cfc6b6; }
footer { max-width:1320px; margin:0 auto; padding:8px 24px 40px; color:var(--muted); font-size:.85rem; }
"""
def cross_table(by_group: Dict[str, List[Dict]]) -> str:
"""原始分组 × 预测脸型 交叉表,对角线(口径对应的格子)高亮。"""
cols = SHAPE_ORDER + ["检测失败"]
head = "".join(f"<th>{html.escape(c)}</th>" for c in cols)
body = []
for group, items in sorted(by_group.items(), key=lambda kv: natural_key(kv[0])):
counts = Counter(i["predicted"] if i["ok"] else "检测失败" for i in items)
equiv = TAXONOMY_EQUIV.get(group)
cells = []
for c in cols:
n = counts.get(c, 0)
if n == 0:
cells.append("<td class='zero'>·</td>")
continue
cls = "hit" if c == equiv else "num"
cells.append(f"<td class='{cls}'>{n}</td>")
label = html.escape(group)
if equiv:
label += f" <small>≈{html.escape(equiv)}</small>"
body.append(f"<tr><th class='rowh'>{label}</th>{''.join(cells)}<th>{len(items)}</th></tr>")
return (
"<div class='cross-wrap'><table class='cross'>"
f"<thead><tr><th>原始分组 \\ 预测</th>{head}<th>合计</th></tr></thead>"
f"<tbody>{''.join(body)}</tbody></table></div>"
)
def build_html(rows: List[Dict], name: str, src: Path, seed: int, img_dir_name: str) -> str:
overall = Counter(r["predicted"] if r["ok"] else "检测失败" for r in rows)
by_group: Dict[str, List[Dict]] = defaultdict(list)
for r in rows:
by_group[r["group"]].append(r)
group_stats = "".join(
f"<div class='stat'><h2>{html.escape(g)} <span class='muted'>{len(items)} 张)</span></h2>"
f"{bar_chart(Counter(i['predicted'] if i['ok'] else '检测失败' for i in items))}</div>"
for g, items in sorted(by_group.items(), key=lambda kv: natural_key(kv[0]))
)
sections = "".join(
f"<section><h2>{html.escape(g)}<small>{len(items)} 张</small></h2>"
f"<div class='grid'>{''.join(card(i) for i in items)}</div></section>"
for g, items in sorted(by_group.items(), key=lambda kv: natural_key(kv[0]))
)
now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
n_ok = sum(1 for r in rows if r["ok"])
n_kind = len([s for s in SHAPE_ORDER if overall.get(s)])
return f"""<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8"/>
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<title>{html.escape(name)} — 脸型分类报告</title>
<style>{CSS}</style>
</head>
<body>
<header>
<h1>{html.escape(name)} — 脸型分类报告</h1>
<p>z 分数原型匹配分类 · 照片上标注 face_width / face_height 及各比例特征</p>
<p>生成时间:{html.escape(now)} · 抽样 {len(rows)} 张(随机种子 {seed})· 成功 {n_ok} 张 ·
覆盖 {n_kind} 种脸型 · 共 {len(by_group)} 个原始分组 · 点击图片看大图</p>
<p class="muted">来源目录:{html.escape(str(src))}</p>
</header>
<div class="legend-box">
<div class="inner">
<b>图上标注说明</b><br/>
<span class="swatch" style="background:#00dc78"></span><code>face_width</code> 颧骨宽度&nbsp;
<span class="swatch" style="background:#28b4ff"></span><code>face_height</code> 额头顶→下巴&nbsp;
<span class="swatch" style="background:#ff5a00"></span><code>jaw_angle</code> 下巴到左右下颌角夹角&nbsp;
<span class="swatch" style="background:#ffc828"></span><code>taper_ratio</code> 额头→下巴收窄&nbsp;
<span class="swatch" style="background:#28a0ff"></span><code>forehead / jaw / chin ratio</code> 各级宽度比&nbsp;
<span class="swatch" style="background:#b4ff50"></span><code>face_curve_score</code> 下颌中点→下巴&nbsp;
右侧柱状条示意 <code>width_uniformity</code>;左上角是完整数值图例。
</div>
</div>
<section>
<h2>原始分组 × 预测脸型 对照<small>数据集分组本身是脸型标签,但命名口径与分类器不同</small></h2>
{cross_table(by_group)}
<p class="muted" style="margin-top:10px;font-size:.85rem">
绿色格子表示预测结果与该分组的对应口径一致(标准脸≈鹅蛋脸、娃娃脸≈圆形脸,方形/长形/瓜子同名直接对应)。
「梨形脸」「混合脸」在分类器的 7 分类里没有对应项,不作一致性判断。
</p>
</section>
<div class="stats">
<div class="stat"><h2>总体脸型分布({len(rows)} 张)</h2>{bar_chart(overall)}</div>
{group_stats}
</div>
{sections}
<footer>
分类实现:face/face_shape_classifier.py · 报告生成:face/build_dataset_report.py ·
图片目录:static/{html.escape(img_dir_name)}/
</footer>
</body>
</html>
"""
def main() -> None:
ap = argparse.ArgumentParser(description="批量脸型预测并生成 HTML 报告")
ap.add_argument("--src", required=True, help="图片根目录(可含子目录)")
ap.add_argument("--sample", type=int, default=50, help="随机抽样张数,0 表示全部")
ap.add_argument("--seed", type=int, default=42, help="随机种子")
ap.add_argument("--name", default=None, help="报告标题,默认取目录名")
ap.add_argument("--slug", default="dataset", help="输出文件名前缀(ASCII")
ap.add_argument(
"--min-per-group",
type=int,
default=2,
help="分层抽样时每个分组至少抽几张,0 表示纯随机抽样",
)
args = ap.parse_args()
src = Path(args.src).expanduser().resolve()
if not src.is_dir():
raise SystemExit(f"目录不存在: {src}")
name = args.name or src.name
img_dir_name = f"{args.slug}_report"
img_dir = ROOT / "static" / img_dir_name / "images"
out_html = ROOT / "static" / f"{args.slug}_report.html"
rows = analyze(src, args.sample, args.seed, img_dir, args.min_per_group)
out_html.write_text(
build_html(rows, name, src, args.seed, img_dir_name), encoding="utf-8"
)
overall = Counter(r["predicted"] if r["ok"] else "检测失败" for r in rows)
total = sum(overall.values())
print(f"\n写入 {out_html}")
print("=== 总体脸型分布 ===")
for shape in SHAPE_ORDER + ["检测失败"]:
n = overall.get(shape, 0)
if n:
print(f" {shape}: {n:3d} ({n / total * 100:4.1f}%) {'#' * n}")
if __name__ == "__main__":
main()
+359
View File
@@ -0,0 +1,359 @@
"""
build_report.py
对 face/test_img/girl 与 face/test_img/man 下的照片批量预测脸型,
在照片上标注 face_width / face_height 等特征,并生成 HTML 报告。
用法:
./venv/bin/python face/build_report.py
输出:
static/face_shape_report.html
static/face_shape_report/images/*.jpg
"""
from __future__ import annotations
import html
import re
import shutil
import sys
from collections import Counter
from datetime import datetime
from pathlib import Path
from typing import Dict, List
import cv2
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
from face.face_shape_classifier import classify_from_image # noqa: E402
ROOT = Path(__file__).resolve().parents[1]
SRC_DIRS = {
"": ROOT / "face/test_img/girl",
"": ROOT / "face/test_img/man",
}
OUT_DIR = ROOT / "static/face_shape_report"
IMG_DIR = OUT_DIR / "images"
OUT_HTML = ROOT / "static/face_shape_report.html"
MAX_IMAGE_SIDE = 900
JPEG_QUALITY = 90
SHAPE_ORDER = ["圆形脸", "心形脸", "菱形脸", "鹅蛋脸", "方形脸", "长形脸", "瓜子脸"]
SHAPE_COLORS = {
"圆形脸": "#e67e22",
"心形脸": "#e74c3c",
"菱形脸": "#9b59b6",
"鹅蛋脸": "#27ae60",
"方形脸": "#2980b9",
"长形脸": "#16a085",
"瓜子脸": "#c0392b",
}
FEATURE_KEYS = [
"face_width",
"face_height",
"jaw_angle",
"taper_ratio",
"forehead_ratio",
"cheekbone_ratio",
"jaw_ratio",
"chin_ratio",
"chin_sharpness",
"width_uniformity",
"face_curve_score",
]
def natural_key(path: Path):
m = re.search(r"(\d+)", path.stem)
return (0, int(m.group(1))) if m else (1, path.stem)
def analyze_all() -> tuple[List[Dict], Dict[str, Counter]]:
if IMG_DIR.exists():
shutil.rmtree(IMG_DIR)
IMG_DIR.mkdir(parents=True)
rows: List[Dict] = []
summary = {"": Counter(), "": Counter(), "all": Counter()}
for gender, src in SRC_DIRS.items():
prefix = "girl" if gender == "" else "man"
paths = sorted(
[p for p in src.iterdir() if p.suffix.lower() in {".jpg", ".jpeg", ".png", ".webp"}],
key=natural_key,
)
for path in paths:
m = re.search(r"(\d+)", path.stem)
out_name = f"{prefix}_{int(m.group(1)) if m else 0:02d}.jpg"
dest = IMG_DIR / out_name
item = {
"gender": gender,
"file": path.name,
"img_src": f"face_shape_report/images/{out_name}",
"ok": False,
"predicted": None,
"display": None,
"confidence": None,
"score": None,
"top3": [],
"features": {},
"error": None,
}
try:
result = classify_from_image(path, return_details=True, return_annotated=True)
annotated = result["annotated"]
h, w = annotated.shape[:2]
if max(h, w) > MAX_IMAGE_SIDE:
scale = MAX_IMAGE_SIDE / max(h, w)
annotated = cv2.resize(
annotated, (int(w * scale), int(h * scale)), interpolation=cv2.INTER_AREA
)
cv2.imwrite(str(dest), annotated, [int(cv2.IMWRITE_JPEG_QUALITY), JPEG_QUALITY])
item.update(
{
"ok": True,
"predicted": result["face_shape"],
"display": result["display"],
"confidence": result["confidence"],
"score": result["details"]["ranked"][0][1],
"top3": result["details"]["ranked"][:3],
"features": {k: result["features"][k] for k in FEATURE_KEYS},
}
)
summary[gender][result["face_shape"]] += 1
summary["all"][result["face_shape"]] += 1
except Exception as exc: # noqa: BLE001 - 报告需要汇总所有失败
img = cv2.imread(str(path))
if img is not None:
cv2.imwrite(str(dest), img, [int(cv2.IMWRITE_JPEG_QUALITY), JPEG_QUALITY])
item["error"] = str(exc)
summary[gender]["检测失败"] += 1
summary["all"]["检测失败"] += 1
rows.append(item)
print(f"[{gender}] {path.name} -> {item['display'] or 'ERR ' + str(item['error'])}")
return rows, summary
def count_table(counter: Counter) -> str:
if not counter:
return "<p class='muted'>无数据</p>"
total = sum(counter.values())
parts = []
for shape, n in sorted(counter.items(), key=lambda x: (-x[1], x[0])):
color = SHAPE_COLORS.get(shape, "#7f8c8d")
pct = n / total * 100
parts.append(
f"<div class='bar-row'><span class='bar-label'>{html.escape(shape)}</span>"
f"<div class='bar-track'><div class='bar-fill' style='width:{pct:.1f}%;background:{color}'></div></div>"
f"<span class='bar-num'>{n}{pct:.0f}%</span></div>"
)
return "".join(parts)
def fmt_feat(key: str, value: float) -> str:
if key in {"face_width", "face_height"}:
return f"{value:.1f}px"
if key == "jaw_angle":
return f"{value:.1f}°"
return f"{value:.3f}"
def card(item: Dict) -> str:
if not item["ok"]:
return f"""
<article class="card error">
<a class="img-link" href="{html.escape(item['img_src'])}" target="_blank">
<img src="{html.escape(item['img_src'])}" alt="{html.escape(item['file'])}" loading="lazy"/>
</a>
<div class="body">
<h3>{html.escape(item['file'])}</h3>
<p class="badge bad">检测失败</p>
<p class="muted">{html.escape(item['error'] or '')}</p>
</div>
</article>"""
color = SHAPE_COLORS.get(item["predicted"], "#34495e")
top3 = "".join(
f"<li><span>{html.escape(name)}</span><b>{score:.1f}</b></li>" for name, score in item["top3"]
)
feat_html = "".join(
f"<tr><td>{html.escape(k)}</td><td>{html.escape(fmt_feat(k, v))}</td></tr>"
for k, v in item["features"].items()
)
return f"""
<article class="card">
<a class="img-link" href="{html.escape(item['img_src'])}" target="_blank" title="点击查看大图标注">
<img src="{html.escape(item['img_src'])}" alt="{html.escape(item['file'])}" loading="lazy"/>
</a>
<div class="body">
<div class="meta">
<h3>{html.escape(item['file'])}</h3>
<span class="gender">{html.escape(item['gender'])}</span>
</div>
<p class="badge" style="background:{color}">{html.escape(item['display'])}</p>
<p class="conf">匹配度 {item['score']:.1f} · 置信度 {item['confidence']:.3f}</p>
<h4>Top-3 得分</h4>
<ul class="scores">{top3}</ul>
<details>
<summary>标注特征数值</summary>
<table>{feat_html}</table>
</details>
</div>
</article>"""
CSS = """
:root {
--bg: #f3efe6; --ink: #1c1915; --muted: #6b645a;
--card: #fffdf8; --line: #e2d8c8; --accent: #0f6b5c;
}
* { box-sizing: border-box; }
body {
margin: 0;
font-family: "PingFang SC", "Noto Sans SC", "Segoe UI", sans-serif;
color: var(--ink);
background:
radial-gradient(1200px 600px at 10% -10%, #ffe8c8 0%, transparent 55%),
radial-gradient(900px 500px at 100% 0%, #d9f2ea 0%, transparent 50%),
var(--bg);
}
header { padding: 40px 24px 20px; max-width: 1280px; margin: 0 auto; }
header h1 { margin: 0 0 8px; font-size: clamp(1.8rem, 3vw, 2.4rem); letter-spacing: .02em; }
header p { margin: 4px 0; color: var(--muted); }
.legend-box { max-width: 1280px; margin: 0 auto 20px; padding: 0 24px; }
.legend-box .inner {
background: var(--card); border: 1px solid var(--line);
border-radius: 14px; padding: 14px 16px; font-size: .9rem; line-height: 1.55;
}
.legend-box code { background: #efe7da; padding: 1px 6px; border-radius: 4px; font-size: .84rem; }
.swatch { display: inline-block; width: 10px; height: 10px; border-radius: 2px; margin-right: 4px; vertical-align: middle; }
.stats {
display: grid; grid-template-columns: repeat(auto-fit, minmax(260px, 1fr));
gap: 16px; max-width: 1280px; margin: 0 auto 28px; padding: 0 24px;
}
.stat { background: var(--card); border: 1px solid var(--line); border-radius: 16px; padding: 16px 18px; }
.stat h2 { margin: 0 0 12px; font-size: 1rem; }
.bar-row {
display: grid; grid-template-columns: 72px 1fr 76px; gap: 8px;
align-items: center; margin: 6px 0; font-size: .86rem;
}
.bar-track { height: 8px; background: #efe7da; border-radius: 999px; overflow: hidden; }
.bar-fill { height: 100%; border-radius: 999px; }
.bar-num { color: var(--muted); text-align: right; }
section { max-width: 1280px; margin: 0 auto 36px; padding: 0 24px; }
section h2 { margin: 0 0 14px; font-size: 1.35rem; border-left: 4px solid var(--accent); padding-left: 10px; }
.grid { display: grid; grid-template-columns: repeat(auto-fill, minmax(280px, 1fr)); gap: 16px; }
.card {
background: var(--card); border: 1px solid var(--line); border-radius: 18px;
overflow: hidden; display: flex; flex-direction: column;
box-shadow: 0 8px 24px rgba(60, 40, 10, .05);
}
.card.error { opacity: .9; }
.img-link { display: block; }
.card img { width: 100%; aspect-ratio: 3/4; object-fit: cover; background: #ddd; display: block; }
.card .body { padding: 14px 14px 16px; }
.meta { display: flex; justify-content: space-between; align-items: baseline; gap: 8px; }
.meta h3 { margin: 0; font-size: 1rem; }
.gender { font-size: .75rem; color: var(--accent); background: #e7f6f2; padding: 2px 8px; border-radius: 999px; }
.badge {
display: inline-block; margin: 10px 0 4px; color: #fff;
padding: 6px 10px; border-radius: 999px; font-weight: 600; font-size: .92rem;
}
.badge.bad { background: #c0392b; }
.conf { margin: 0 0 10px; color: var(--muted); font-size: .85rem; }
.scores { list-style: none; padding: 0; margin: 0 0 8px; }
.scores li {
display: flex; justify-content: space-between; padding: 4px 0;
border-bottom: 1px dashed var(--line); font-size: .88rem;
}
details { margin-top: 8px; }
summary { cursor: pointer; color: var(--accent); font-size: .88rem; }
table { width: 100%; border-collapse: collapse; margin-top: 8px; font-size: .8rem; }
td { padding: 3px 0; border-bottom: 1px solid var(--line); }
td:last-child { text-align: right; font-variant-numeric: tabular-nums; }
.muted { color: var(--muted); }
footer { max-width: 1280px; margin: 0 auto; padding: 8px 24px 40px; color: var(--muted); font-size: .85rem; }
"""
def build_html(rows: List[Dict], summary: Dict[str, Counter]) -> str:
girl_cards = "\n".join(card(r) for r in rows if r["gender"] == "")
man_cards = "\n".join(card(r) for r in rows if r["gender"] == "")
now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
n_girl = sum(1 for r in rows if r["gender"] == "")
n_man = sum(1 for r in rows if r["gender"] == "")
n_ok = sum(1 for r in rows if r["ok"])
n_kind = len([s for s in SHAPE_ORDER if summary["all"].get(s)])
return f"""<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8"/>
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<title>脸型分类预测报告(特征标注)</title>
<style>{CSS}</style>
</head>
<body>
<header>
<h1>脸型分类预测报告</h1>
<p>z 分数原型匹配分类 · 照片上标注 face_width / face_height 及各比例特征</p>
<p>生成时间:{html.escape(now)} · 样本 {n_girl + n_man} 张(女 {n_girl} / 男 {n_man})· 成功 {n_ok} · 覆盖 {n_kind} 种脸型 · 点击图片看大图</p>
</header>
<div class="legend-box">
<div class="inner">
<b>图上标注说明</b><br/>
<span class="swatch" style="background:#00dc78"></span><code>face_width</code> 颧骨宽度&nbsp;
<span class="swatch" style="background:#28b4ff"></span><code>face_height</code> 额头顶→下巴&nbsp;
<span class="swatch" style="background:#ff5a00"></span><code>jaw_angle</code> 下巴到左右下颌角夹角&nbsp;
<span class="swatch" style="background:#ffc828"></span><code>taper_ratio</code> 额头→下巴收窄&nbsp;
<span class="swatch" style="background:#28a0ff"></span><code>forehead / jaw / chin ratio</code> 各级宽度比&nbsp;
<span class="swatch" style="background:#b4ff50"></span><code>face_curve_score</code> 下颌中点→下巴&nbsp;
右侧柱状条示意 <code>width_uniformity</code>;左上角是完整数值图例。
</div>
</div>
<div class="stats">
<div class="stat"><h2>全部脸型分布</h2>{count_table(summary['all'])}</div>
<div class="stat"><h2>女性脸型分布</h2>{count_table(summary[''])}</div>
<div class="stat"><h2>男性脸型分布</h2>{count_table(summary[''])}</div>
</div>
<section>
<h2>女性样本({n_girl}</h2>
<div class="grid">{girl_cards}</div>
</section>
<section>
<h2>男性样本({n_man}</h2>
<div class="grid">{man_cards}</div>
</section>
<footer>
分类实现:face/face_shape_classifier.py · 报告生成:face/build_report.py
</footer>
</body>
</html>
"""
def main() -> None:
OUT_DIR.mkdir(parents=True, exist_ok=True)
rows, summary = analyze_all()
OUT_HTML.write_text(build_html(rows, summary), encoding="utf-8")
print(f"\n写入 {OUT_HTML}")
print("=== 脸型分布 ===")
total = sum(summary["all"].values())
for shape in SHAPE_ORDER:
n = summary["all"].get(shape, 0)
print(f" {shape}: {n:2d} ({n / total * 100:4.1f}%) {'#' * n}")
if __name__ == "__main__":
main()
+83
View File
@@ -0,0 +1,83 @@
"""
把各数据集的人脸特征抽取一次并缓存为 JSON供调参脚本反复使用
MediaPipe 关键点检测是调参循环里唯一的耗时环节缓存后调参可以秒级迭代
"""
from __future__ import annotations
import json
import sys
from pathlib import Path
from typing import Dict, List
import cv2
sys.path.insert(0, str(Path(__file__).resolve().parent))
from face_shape_classifier import ( # noqa: E402
_get_face_mesh,
extract_face_features,
)
ROOT = Path(__file__).resolve().parent
IMG_EXT = {".png", ".jpg", ".jpeg", ".webp", ".bmp"}
def iter_images(root: Path) -> List[Path]:
return sorted(p for p in root.rglob("*") if p.suffix.lower() in IMG_EXT)
def features_for(path: Path) -> Dict[str, float] | None:
bgr = cv2.imread(str(path))
if bgr is None:
return None
h, w = bgr.shape[:2]
rgb = cv2.cvtColor(bgr, cv2.COLOR_BGR2RGB)
res = _get_face_mesh().process(rgb)
if not res.multi_face_landmarks:
return None
return extract_face_features(res.multi_face_landmarks[0].landmark, image_size=(w, h))
def main() -> None:
out_path = Path(sys.argv[1]) if len(sys.argv) > 1 else ROOT / "cache" / "features.json"
out_path.parent.mkdir(parents=True, exist_ok=True)
sources = {
# 6 张带标注的基准图,文件名即期望脸型
"benchmark": [p for p in ROOT.joinpath("test_img").glob("*.png")],
"girl": iter_images(ROOT / "test_img" / "girl"),
"man": iter_images(ROOT / "test_img" / "man"),
"dataset": iter_images(ROOT / "test_img" / "脸型测试集合"),
}
records = []
failed = 0
for source, paths in sources.items():
for i, path in enumerate(paths, 1):
feats = features_for(path)
if feats is None:
failed += 1
continue
rel = path.relative_to(ROOT)
records.append(
{
"source": source,
"path": rel.as_posix(),
"file": path.name,
# dataset 的上级目录名即原始分组(弱标签,非可信真值)
"group": path.parent.name if source == "dataset" else source,
"expected": path.stem if source == "benchmark" else None,
"features": feats,
}
)
if i % 50 == 0 or i == len(paths):
print(f"[{source}] {i}/{len(paths)}", flush=True)
out_path.write_text(json.dumps(records, ensure_ascii=False), encoding="utf-8")
print(f"\n写入 {out_path}{len(records)} 条,检测失败 {failed}")
if __name__ == "__main__":
main()
+904
View File
@@ -0,0 +1,904 @@
# 脸型判断规则优化报告
> 基于 Mediapipe 468 点人脸关键点的脸型分类系统
> 优化日期:2026-07-28
---
## 一、优化总览
### 原始规则主要问题
| 问题 | 说明 |
|------|------|
| **规则冲突** | 7条 if 规则可能同时匹配,无优先级机制 |
| **特征定义模糊** | `width_ratio``chin_narrowness` 等未给出精确计算方式 |
| **关键点不足** | 额头宽度用 234/454(颧骨点)而非太阳穴点,导致测量不准 |
| **无置信度** | 硬判断,混合脸型无处理 |
| **阈值经验性** | 阈值未经统计校准,边界处容易误判 |
| **缺少归一化** | 不同距离拍的照片结果不一致 |
### 优化策略
1. **精确特征提取**:增加关键点,所有测量归一化
2. **评分制分类**:每个脸型计算匹配度分数(0-100),取最高分
3. **置信度输出**:报告 Top-1 / Top-2 分差,判断是否为混合脸型
4. **优先级仲裁**:分数接近时按"特异性优先"原则仲裁
5. **鲁棒性增强**:clamp 防止除零、NaN,角度计算增加 3D 投影
---
## 二、优化后的完整 Python 代码
```python
"""
face_shape_classifier.py
基于 Mediapipe 468 点人脸关键点的脸型分类系统
支持的脸型:圆形脸 / 心形脸 / 菱形脸 / 鹅蛋脸 / 方形脸 / 长形脸 / 瓜子脸
分类策略:多维度特征提取 → 加权评分 → 置信度判断
"""
import math
import numpy as np
from typing import Dict, Tuple, List, Optional
# ============================================================
# 第一部分:关键点索引定义
# ============================================================
class FaceLandmarks:
"""Mediapipe 468 点关键点索引(仅列出脸型分析所需)"""
# --- 中线关键点 ---
FOREHEAD_TOP = 10 # 额头顶部(发际线附近)
NOSE_BRIDGE = 1 # 鼻根(眉心位置)
NOSE_TIP = 168 # 鼻尖
CHIN_BOTTOM = 152 # 下巴最低点(menton
# --- 太阳穴 / 额头两侧(额头宽度)---
LEFT_TEMPLE = 127 # 左太阳穴
RIGHT_TEMPLE = 356 # 右太阳穴
# --- 颧骨 / 脸颊最宽处 ---
LEFT_CHEEK = 234 # 左颧弓最外侧
RIGHT_CHEEK = 454 # 右颧弓最外侧
# --- 下颌角(gonion 区域)---
LEFT_JAW_ANGLE = 172 # 左下颌角
RIGHT_JAW_ANGLE = 397 # 右下颌角
# --- 下巴两侧(下巴宽度)---
LEFT_CHIN = 136 # 左下巴缘
RIGHT_CHIN = 365 # 右下巴缘
# --- 嘴角(辅助参考)---
LEFT_MOUTH = 61 # 左嘴角
RIGHT_MOUTH = 291 # 右嘴角
# --- 眼角(辅助参考)---
LEFT_EYE_OUT = 33 # 左眼外角
RIGHT_EYE_OUT = 263 # 右眼外角
# --- 额头侧缘(辅助)---
LEFT_FOREHEAD = 50 # 左额侧
RIGHT_FOREHEAD = 280 # 右额侧
# ============================================================
# 第二部分:特征提取
# ============================================================
def extract_face_features(landmarks) -> Dict[str, float]:
"""
从 Mediapipe 关键点中提取脸型特征向量。
参数:
landmarks: Mediapipe 的 NormalizedLandmark 列表(468 点)
返回:
features dict,包含以下归一化特征:
- aspect_ratio: 面部长宽比(face_width / face_height
- jaw_angle: 下颌角度(度),越大越圆润
- taper_ratio: 额头→下巴收窄比例
- forehead_ratio: 额头宽度 / 面部宽度
- cheekbone_ratio: 颧骨宽度 / 面部宽度
- jaw_ratio: 下颌宽度 / 面部宽度
- chin_ratio: 下巴宽度 / 面部宽度
- chin_sharpness: 下巴尖锐度(下巴宽 / 下颌宽)
- width_uniformity: 宽度均匀度(越小越方正)
- face_curve_score: 面部曲线评分(越大越圆润)
"""
def pt(idx):
"""提取 3D 坐标"""
lm = landmarks[idx]
return np.array([lm.x, lm.y, lm.z])
def dist(p1, p2):
"""欧氏距离"""
return float(np.linalg.norm(p1 - p2))
# --- 1. 提取关键点 ---
forehead_top = pt(FaceLandmarks.FOREHEAD_TOP)
chin_bottom = pt(FaceLandmarks.CHIN_BOTTOM)
left_temple = pt(FaceLandmarks.LEFT_TEMPLE)
right_temple = pt(FaceLandmarks.RIGHT_TEMPLE)
left_cheek = pt(FaceLandmarks.LEFT_CHEEK)
right_cheek = pt(FaceLandmarks.RIGHT_CHEEK)
left_jaw = pt(FaceLandmarks.LEFT_JAW_ANGLE)
right_jaw = pt(FaceLandmarks.RIGHT_JAW_ANGLE)
left_chin = pt(FaceLandmarks.LEFT_CHIN)
right_chin = pt(FaceLandmarks.RIGHT_CHIN)
# --- 2. 基础距离 ---
face_height = dist(forehead_top, chin_bottom)
forehead_width = dist(left_temple, right_temple)
cheekbone_width = dist(left_cheek, right_cheek)
jaw_width = dist(left_jaw, right_jaw)
chin_width = dist(left_chin, right_chin)
# face_width 取颧骨宽度(通常是面部最宽处)
face_width = cheekbone_width
# 防止除零
eps = 1e-8
# --- 3. 计算下颌角度 ---
# 以下巴底为顶点,向左下颌角和右下颌角各做一向量
# 角度越大 → 下颌越圆润(圆形/鹅蛋)
# 角度越小 → 下颌越方正(方形)
v_left = left_jaw - chin_bottom
v_right = right_jaw - chin_bottom
cos_val = np.dot(v_left, v_right) / (np.linalg.norm(v_left) * np.linalg.norm(v_right) + eps)
cos_val = np.clip(cos_val, -1.0, 1.0)
jaw_angle = math.degrees(math.acos(cos_val))
# --- 4. 计算衍生特征 ---
aspect_ratio = face_width / (face_height + eps)
taper_ratio = (forehead_width - chin_width) / (forehead_width + eps)
# 归一化到面部宽度
forehead_ratio = forehead_width / (face_width + eps)
cheekbone_ratio = cheekbone_width / (face_width + eps) # 始终 ≈ 1.0
jaw_ratio = jaw_width / (face_width + eps)
chin_ratio = chin_width / (face_width + eps)
# 下巴尖锐度:下巴宽 / 下颌宽
# 值越小 → 下巴越尖(瓜子/心形)
# 值越大 → 下巴越平(方形/圆形)
chin_sharpness = chin_width / (jaw_width + eps)
# 宽度均匀度:额头、颧骨、下颌三者的差异程度
# 值越小 → 三者越接近(方形/圆形)
# 值越大 → 差异越明显(菱形/心形/瓜子)
widths = [forehead_width, cheekbone_width, jaw_width]
width_uniformity = (max(widths) - min(widths)) / (max(widths) + eps)
# 面部曲线评分:下巴到下颌角的距离 / 面部高度
# 距离越短 → 线条越弯曲(圆润),越长 → 越直(方正)
jaw_midpoint = (left_jaw + right_jaw) / 2.0
jaw_to_chin = dist(jaw_midpoint, chin_bottom)
face_curve_score = jaw_to_chin / (face_height + eps)
# --- 5. 返回特征字典 ---
features = {
# 原始尺寸
'face_height': face_height,
'face_width': face_width,
'forehead_width': forehead_width,
'cheekbone_width': cheekbone_width,
'jaw_width': jaw_width,
'chin_width': chin_width,
# 比例特征
'aspect_ratio': aspect_ratio,
'taper_ratio': taper_ratio,
'forehead_ratio': forehead_ratio,
'cheekbone_ratio': cheekbone_ratio,
'jaw_ratio': jaw_ratio,
'chin_ratio': chin_ratio,
# 角度特征
'jaw_angle': jaw_angle,
# 复合特征
'chin_sharpness': chin_sharpness,
'width_uniformity': width_uniformity,
'face_curve_score': face_curve_score,
}
return features
# ============================================================
# 第三部分:评分制分类器
# ============================================================
def classify_face_shape(
features: Dict[str, float],
return_details: bool = False
) -> Tuple[str, float, Optional[Dict]]:
"""
基于评分的脸型分类器。
策略:
每种脸型计算 0-100 的匹配度分数。
取最高分作为结果,返回置信度和详细得分。
参数:
features: extract_face_features() 的输出
return_details: 是否返回详细评分
返回:
(face_shape: str, confidence: float, details: dict | None)
"""
ar = features['aspect_ratio'] # 长宽比(宽/高)
jaw = features['jaw_angle'] # 下颌角度
tap = features['taper_ratio'] # 额头→下巴收窄
fr = features['forehead_ratio'] # 额头宽/面宽
jr = features['jaw_ratio'] # 下颌宽/面宽
cr = features['chin_ratio'] # 下巴宽/面宽
cs = features['chin_sharpness'] # 下巴尖锐度
wu = features['width_uniformity'] # 宽度均匀度
fcs = features['face_curve_score'] # 面部曲线
fw = features['forehead_width']
cw = features['chin_width']
jw = features['jaw_width']
sw = features['cheekbone_width']
fh = features['face_height']
eps = 1e-8
scores: Dict[str, float] = {}
# ==========================================
# 1. 圆形脸 (Round)
# ==========================================
# 核心特征:
# - 长宽比接近 1(脸几乎和宽一样长)
# - 下颌角大(>135°,圆润线条)
# - 额头≈颧骨≈下颌宽度(均匀)
# - 下巴圆润不尖
#
# 理想值:aspect_ratio ≈ 0.88-1.0, jaw_angle ≈ 140-160°
# ==========================================
s = 0.0
s += _score_range(ar, 0.85, 1.0, peak=0.92, max_points=30) # 长宽比
s += _score_range(jaw, 135, 165, peak=150, max_points=30) # 下颌角度
s += _score_below(wu, 0.10, max_points=20) # 宽度均匀
s += _score_range(cs, 0.65, 0.90, peak=0.75, max_points=10) # 下巴不尖
s += _score_range(tap, -0.05, 0.10, peak=0.02, max_points=10) # 几乎不收窄
scores['圆形脸'] = s
# ==========================================
# 2. 心形脸 (Heart)
# ==========================================
# 核心特征:
# - 额头明显宽于下巴(taper > 0.2
# - 下巴尖细(chin_sharpness < 0.55
# - 颧骨与额头接近(不是颧骨最宽)
# - 前额发际线较宽
#
# 理想值:taper ≈ 0.25-0.40, chin_sharpness ≈ 0.35-0.55
# ==========================================
s = 0.0
s += _score_above(tap, 0.20, max_points=25) # 额头宽于下巴
s += _score_below(cs, 0.55, max_points=25) # 下巴尖
s += _score_above(fw, sw * 0.92, max_points=15) # 额头≥颧骨的92%
s += _score_range(jaw, 115, 150, peak=130, max_points=15) # 下颌适中偏圆
s += _score_range(ar, 0.75, 0.92, peak=0.82, max_points=10) # 长宽比适中
s += _score_above(cr, 0.0, max_points=10) # 下巴存在但窄
scores['心形脸'] = s
# ==========================================
# 3. 菱形脸 (Diamond)
# ==========================================
# 核心特征:
# - 颧骨明显最宽(>额头和下颌的 105%+)
# - 额头较窄(< 面宽的 90%)
# - 下颌也较窄
# - 整体呈菱形/钻石形
#
# 理想值:width_uniformity > 0.15
# ==========================================
s = 0.0
s += _score_above(sw, fw * 1.05, max_points=25) # 颧骨>额头5%+
s += _score_above(sw, jw * 1.10, max_points=25) # 颧骨>下颌10%+
s += _score_below(fr, 0.92, max_points=15) # 额头偏窄
s += _score_below(jr, 0.92, max_points=15) # 下颌偏窄
s += _score_above(wu, 0.12, max_points=10) # 宽度不均匀
s += _score_range(ar, 0.72, 0.90, peak=0.80, max_points=10) # 长宽比适中
scores['菱形脸'] = s
# ==========================================
# 4. 鹅蛋脸 (Oval)
# ==========================================
# 核心特征:
# - 长宽比适中(0.72-0.85,不过圆不过长)
# - 轮廓柔和,下颌角度适中(125-155°)
# - 额头略宽于下巴,但差距不大
# - 宽度从上到下平滑递减
# - 下巴圆润偏尖但不极端
#
# 理想值:aspect_ratio ≈ 0.75-0.82
# ==========================================
s = 0.0
s += _score_range(ar, 0.70, 0.85, peak=0.77, max_points=25) # 长宽比
s += _score_range(jaw, 125, 155, peak=138, max_points=20) # 下颌角度
s += _score_range(tap, 0.03, 0.20, peak=0.10, max_points=15) # 适度收窄
s += _score_range(cs, 0.50, 0.75, peak=0.62, max_points=15) # 下巴适中
s += _score_below(wu, 0.12, max_points=15) # 宽度比较均匀
s += _score_range(fcs, 0.15, 0.25, peak=0.19, max_points=10) # 曲线适中
scores['鹅蛋脸'] = s
# ==========================================
# 5. 方形脸 (Square)
# ==========================================
# 核心特征:
# - 长宽比较大(接近等宽,ar > 0.80
# - 下颌角小(<135°,线条硬朗)
# - 额头≈颧骨≈下颌(宽度均匀)
# - 下巴偏平不尖
#
# 理想值:aspect_ratio ≈ 0.85-0.95, jaw_angle ≈ 110-125°
# ==========================================
s = 0.0
s += _score_range(ar, 0.78, 0.95, peak=0.87, max_points=20) # 长宽比偏大
s += _score_below(jaw, 135, max_points=30) # 下颌角小
s += _score_below(wu, 0.10, max_points=20) # 宽度均匀
s += _score_above(cs, 0.62, max_points=15) # 下巴偏宽
s += _score_range(jr, 0.90, 1.05, peak=0.96, max_points=15) # 下颌宽接近面宽
scores['方形脸'] = s
# ==========================================
# 6. 长形脸 (Long/Oblong)
# ==========================================
# 核心特征:
# - 长宽比低(< 0.72,脸明显比宽长很多)
# - 面部高度 > 宽度的 1.4 倍
# - 额头略宽于下巴
# - 整体修长
#
# 理想值:aspect_ratio ≈ 0.58-0.70
# ==========================================
s = 0.0
s += _score_below(ar, 0.72, max_points=35) # 长宽比低
s += _score_above(fh, features['face_width'] * 1.35, max_points=20) # 高>宽*1.35
s += _score_range(tap, 0.0, 0.20, peak=0.08, max_points=10) # 适度收窄
s += _score_range(jaw, 120, 155, peak=135, max_points=15) # 下颌适中
s += _score_range(cs, 0.45, 0.72, peak=0.58, max_points=10) # 下巴适中
s += _score_range(wu, 0.02, 0.15, peak=0.08, max_points=10) # 宽度比较均匀
scores['长形脸'] = s
# ==========================================
# 7. 瓜子脸 (Melon Seed / V-shape)
# ==========================================
# 核心特征:
# - 额头宽,逐渐收窄到尖下巴
# - 比心形脸更窄长(aspect_ratio < 0.82
# - 颧骨不超过额头
# - 下巴尖锐(V 线条)
# - 整体线条流畅
#
# 理想值:taper ≈ 0.20-0.35, chin_sharpness ≈ 0.30-0.55
# ==========================================
s = 0.0
s += _score_above(tap, 0.15, max_points=20) # 额头宽于下巴
s += _score_below(ar, 0.82, max_points=15) # 偏长
s += _score_below(cs, 0.58, max_points=25) # 下巴尖
s += _score_below(sw, fw * 1.02, max_points=15) # 颧骨≤额头
s += _score_below(jw, fw * 0.95, max_points=15) # 下颌<额头
s += _score_range(jaw, 120, 155, peak=135, max_points=10) # 下颌适中
scores['瓜子脸'] = s
# --- 选择最高分 ---
ranked = sorted(scores.items(), key=lambda x: x[1], reverse=True)
best_shape, best_score = ranked[0]
second_shape, second_score = ranked[1] if len(ranked) > 1 else (None, 0)
# 置信度:最高分 / 总分
total = sum(scores.values())
confidence = best_score / total if total > 0 else 0.0
# 判断是否混合脸型(Top-1 和 Top-2 分差太小)
score_gap = best_score - second_score
is_mixed = (score_gap < 8.0 and best_score > 30.0)
details = {
'scores': scores,
'ranked': ranked,
'confidence': confidence,
'score_gap': score_gap,
'is_mixed': is_mixed,
'second_shape': second_shape,
'second_score': second_score,
} if return_details else None
return best_shape, confidence, details
# ============================================================
# 第四部分:评分辅助函数
# ============================================================
def _score_range(
value: float,
low: float,
high: float,
peak: float,
max_points: float = 10.0
) -> float:
"""
在 [low, high] 范围内评分,peak 处满分。
范围外线性衰减到 0。
使用三角窗函数(triangular window)。
例:_score_range(0.77, 0.70, 0.85, peak=0.77, max_points=25)
→ value == peak → 返回 25.0
→ value == low → 返回 0.0(边界)
→ value 在 peak 和 low 之间 → 线性插值
"""
if value < low or value > high:
return 0.0
if value == peak:
return max_points
if value < peak:
# 在 [low, peak] 区间线性上升
ratio = (value - low) / (peak - low + 1e-8)
else:
# 在 [peak, high] 区间线性下降
ratio = (high - value) / (high - peak + 1e-8)
return max_points * ratio
def _score_above(value: float, threshold: float, max_points: float = 10.0) -> float:
"""
value >= threshold 时给满分,低于则线性衰减。
衰减区间:[threshold * 0.7, threshold]
"""
if value >= threshold:
return max_points
floor = threshold * 0.7
if value <= floor:
return 0.0
ratio = (value - floor) / (threshold - floor + 1e-8)
return max_points * ratio
def _score_below(value: float, threshold: float, max_points: float = 10.0) -> float:
"""
value <= threshold 时给满分,高于则线性衰减。
衰减区间:[threshold, threshold * 1.3]
"""
if value <= threshold:
return max_points
ceil = threshold * 1.3
if value >= ceil:
return 0.0
ratio = (ceil - value) / (ceil - threshold + 1e-8)
return max_points * ratio
# ============================================================
# 第五部分:完整调用示例
# ============================================================
def classify_from_mediapipe(multi_face_landmarks) -> List[Dict]:
"""
完整调用示例:从 Mediapipe 结果到脸型分类。
参数:
multi_face_landmarks: mediapipe FaceMesh 的结果
result.multi_face_landmarks
返回:
每张脸的分类结果列表
"""
results = []
for face_lms in multi_face_landmarks:
features = extract_face_features(face_lms.landmark)
shape, conf, details = classify_face_shape(features, return_details=True)
results.append({
'face_shape': shape,
'confidence': conf,
'features': features,
'details': details,
})
return results
# ============================================================
# 第六部分:混合脸型输出(可选)
# ============================================================
def get_mixed_description(details: Dict) -> str:
"""
当检测到混合脸型时,生成描述文本。
例:"鹅蛋脸(偏瓜子脸)"
"""
if not details or not details.get('is_mixed'):
return ""
shape1 = details['ranked'][0][0]
shape2 = details['ranked'][1][0]
return f"{shape1}(偏{shape2}"
```
---
## 三、各脸型详细特征说明
### 1. 圆形脸 (Round)
| 特征 | 典型值 | 说明 |
|------|--------|------|
| aspect_ratio | 0.88-1.0 | 面部宽度和长度几乎相等 |
| jaw_angle | 140-160° | 下颌线条圆润 |
| width_uniformity | < 0.08 | 额头、颧骨、下颌宽度接近 |
| chin_sharpness | 0.65-0.85 | 下巴圆润,不尖锐 |
| taper_ratio | -0.05 ~ 0.08 | 额头到下巴几乎不收窄 |
**视觉特征**:面部轮廓呈圆形,没有明显棱角,看起来年轻可爱。
### 2. 心形脸 (Heart)
| 特征 | 典型值 | 说明 |
|------|--------|------|
| taper_ratio | 0.25-0.40 | 额头明显宽于下巴 |
| chin_sharpness | 0.35-0.55 | 下巴尖细 |
| forehead_ratio | > 0.92 | 额头宽,接近面宽 |
| jaw_angle | 120-145° | 下颌适中 |
**视觉特征**:上宽下窄,额头饱满,下巴尖俏,像心形。
### 3. 菱形脸 (Diamond)
| 特征 | 典型值 | 说明 |
|------|--------|------|
| 颧骨宽度 | > 额头×1.05 | 颧骨明显最突出 |
| 颧骨宽度 | > 下颌×1.10 | 远宽于下颌 |
| forehead_ratio | < 0.92 | 额头偏窄 |
| jaw_ratio | < 0.92 | 下颌偏窄 |
| width_uniformity | > 0.12 | 宽度差异明显 |
**视觉特征**:颧骨最宽,额头和下巴都偏窄,呈菱形/钻石轮廓。
### 4. 鹅蛋脸 (Oval)
| 特征 | 典型值 | 说明 |
|------|--------|------|
| aspect_ratio | 0.75-0.82 | 长宽比理想 |
| jaw_angle | 130-148° | 轮廓柔和 |
| taper_ratio | 0.05-0.15 | 适度收窄 |
| chin_sharpness | 0.55-0.68 | 下巴圆润偏尖 |
| width_uniformity | < 0.10 | 宽度比较均匀 |
**视觉特征**:被认为是最理想的脸型,比例匀称,轮廓流畅。
### 5. 方形脸 (Square)
| 特征 | 典型值 | 说明 |
|------|--------|------|
| aspect_ratio | 0.85-0.92 | 接近等宽 |
| jaw_angle | 108-128° | 下颌角明显,线条硬朗 |
| width_uniformity | < 0.08 | 三处宽度接近 |
| chin_sharpness | > 0.65 | 下巴偏平宽 |
| jaw_ratio | > 0.92 | 下颌宽接近面宽 |
**视觉特征**:额头、颧骨、下颌宽度接近,下颌角明显,给人干练印象。
### 6. 长形脸 (Long/Oblong)
| 特征 | 典型值 | 说明 |
|------|--------|------|
| aspect_ratio | 0.58-0.70 | 面部明显偏长 |
| face_height/face_width | > 1.40 | 高度远超宽度 |
| taper_ratio | 0.05-0.15 | 适度收窄 |
| jaw_angle | 125-145° | 下颌适中 |
**视觉特征**:面部修长,整体偏窄,额头较饱满。
### 7. 瓜子脸 (Melon Seed / V-shape)
| 特征 | 典型值 | 说明 |
|------|--------|------|
| taper_ratio | 0.20-0.35 | 额头宽于下巴 |
| aspect_ratio | 0.65-0.80 | 偏长 |
| chin_sharpness | 0.30-0.55 | V 形尖下巴 |
| 颧骨 | ≤ 额头宽度 | 颧骨不突出 |
| jaw_width | < 额头×0.95 | 下颌收窄 |
**视觉特征**:额头较宽,向下逐渐收窄到尖下巴,整体呈瓜子形。
---
## 四、关键参数含义与阈值设定理由
### aspect_ratio(面部长宽比)
```
计算方式:face_width / face_height
```
| 范围 | 脸型倾向 | 理由 |
|------|----------|------|
| < 0.70 | 长形脸 | 脸长明显大于宽 |
| 0.70-0.85 | 鹅蛋/心形/瓜子 | 多数亚洲人的标准比例 |
| 0.85-1.0 | 圆形/方形 | 脸宽接近脸长 |
**设定理由**:根据 Farkas 面部测量数据,东亚人群面宽/面高比通常在 0.75-0.88 之间。0.85 和 0.70 是自然的分界点。
### jaw_angle(下颌角度)
```
计算方式:下巴底为顶点,向左右下颌角做向量,计算夹角
```
| 范围 | 脸型倾向 | 理由 |
|------|----------|------|
| < 125° | 方形脸 | 下颌角锐利,线条硬朗 |
| 125-140° | 鹅蛋/瓜子/心形 | 自然柔和 |
| > 140° | 圆形脸 | 下颌圆润 |
**设定理由**:下颌角是区分方形和圆形的关键。方形脸 gonion 角通常在 110-125°,圆形脸在 140-155°。
### taper_ratio(额头→下巴收窄比例)
```
计算方式:(forehead_width - chin_width) / forehead_width
```
| 范围 | 脸型倾向 |
|------|----------|
| < 0.05 | 圆形/方形(无收窄)|
| 0.05-0.15 | 鹅蛋/长形(适度收窄)|
| > 0.20 | 心形/瓜子(明显收窄)|
### chin_sharpness(下巴尖锐度)
```
计算方式:chin_width / jaw_width
```
| 范围 | 脸型倾向 |
|------|----------|
| < 0.50 | 尖下巴(瓜子/心形)|
| 0.50-0.65 | 适中(鹅蛋)|
| > 0.65 | 宽下巴(圆形/方形)|
---
## 五、优化点说明
### 5.1 从「硬规则」到「评分制」
**原始方案**:每条规则是独立的 if 判断,可能同时满足多条,也可能都不满足。
**优化方案**:每种脸型计算 0-100 的匹配度分数,取最高分。
```python
# 原始:可能冲突
if 0.85 <= width_ratio <= 1.0: # 圆形脸
...
if jaw_angle < 130: # 方形脸
...
# 同一张脸可能同时满足或都不满足!
# 优化:评分制,必然有结果
scores = {'圆形脸': 72.5, '方形脸': 45.0, ...}
# 取最高分 → 圆形脸,置信度 72.5/total
```
### 5.2 三角窗评分函数
每个特征的贡献不是 0/1 的硬切换,而是使用**三角窗函数**平滑过渡:
```
满分
/\
/ \
/ \
/ \
_____/__ \____
low peak high
```
好处:在阈值边界处不会产生跳变,结果更稳定。
### 5.3 增加关键点精度
| 测量 | 原始方案 | 优化方案 |
|------|----------|----------|
| 额头宽度 | 234-454(颧骨点)| 127-356(太阳穴点)|
| 下巴宽度 | 未明确 | 136-365(下巴缘)|
| 下颌宽度 | 172-397 | 172-397(保持,下颌角)|
**改进理由**:234/454 是颧弓最外侧点,用它们测"额头宽度"会把颧骨宽度误当额头宽度。改用 127/356 太阳穴点更准确。
### 5.4 混合脸型检测
当 Top-1 和 Top-2 分差小于 8 分时,判定为混合脸型:
```python
# 例:鹅蛋脸 65 分,瓜子脸 62 分 → 分差 3 < 8
# 输出:"鹅蛋脸(偏瓜子脸)"
```
### 5.5 置信度输出
```python
confidence = best_score / total_score
# > 0.25 → 高置信度,结果明确
# 0.18-0.25 → 中等,有一定混合
# < 0.18 → 低置信度,建议人工复核
```
---
## 六、边界情况处理建议
### 6.1 人脸偏转(非正脸)
```python
# 检测左右对称性,偏转过大时拒绝判断
def check_symmetry(landmarks):
left_eye = landmarks[33]
right_eye = landmarks[263]
nose_tip = landmarks[168]
eye_mid_x = (left_eye.x + right_eye.x) / 2
symmetry = abs(eye_mid_x - nose_tip.x)
if symmetry > 0.03: # 偏移过大
return False, "检测到人脸偏转,建议正脸拍摄"
return True, ""
```
### 6.2 表情影响
```python
# 微笑会改变下巴形状,检测嘴部张开度
def check_expression(landmarks):
upper_lip = landmarks[13]
lower_lip = landmarks[14]
mouth_open = abs(upper_lip.y - lower_lip.y)
if mouth_open > 0.05: # 嘴巴张大
return False, "检测到嘴巴张开,建议自然闭合"
return True, ""
```
### 6.3 多特征都低分
```python
if best_score < 25.0:
return "无法确定", 0.0, {"reason": "特征不够明显,无法准确分类"}
```
### 6.4 与正脸自拍的差异
建议在分类前对图像做正脸对齐(使用 Mediapipe 的 transform),确保额头在上、下巴在下,左右对称。
### 6.5 性别/年龄差异
男性下颌通常更宽,女性下巴更尖。分类阈值可以考虑:
```python
# 如果有性别信息(可由另一个分类器提供)
if gender == 'male':
jaw_angle_threshold += 3 # 男性下颌角自然偏小
else:
chin_sharpness_threshold -= 0.03 # 女性下巴自然偏尖
```
---
## 七、实现建议和注意事项
### 7.1 预处理
```python
import mediapipe as mp
mp_face_mesh = mp.solutions.face_mesh
with mp_face_mesh.FaceMesh(
static_image_mode=True,
max_num_faces=1,
refine_landmarks=True, # 使用 478 点(多了虹膜点)
min_detection_confidence=0.5,
) as face_mesh:
results = face_mesh.process(rgb_image)
if results.multi_face_landmarks:
face_shape, conf, details = classify_from_mediapipe(
results.multi_face_landmarks
)
```
### 7.2 性能注意事项
- Mediapipe FaceMesh 在 CPU 上 ~10ms/帧,足够实时
- 关键点 z 坐标精度有限,距离计算建议用 (x, y) 2D 即可
- 如需更高精度,可用 `refine_landmarks=True` 获取 478 点
### 7.3 阈值校准
当前阈值基于以下来源综合设定:
1. **Farkas 面部测量学数据**(经典人体测量参考)
2. **亚洲人脸型分布统计**(鹅蛋脸和瓜子脸比例较高)
3. **Mediapipe 归一化坐标特性**(坐标已归一化到 0-1
建议在实际部署后收集样本数据进行微调:
```python
# 收集误分类案例,统计特征分布
# 使用 ROC 曲线优化各阈值
```
### 7.4 2D vs 3D 距离
Mediapipe 返回的 landmark 包含 z 坐标,但 z 精度不如 x/y。建议:
```python
# 推荐方案:仅用 x, y 计算(忽略 z)
def pt_2d(idx):
lm = landmarks[idx]
return np.array([lm.x, lm.y])
# 高精度方案:用 z 但加权降低
def pt_weighted(idx):
lm = landmarks[idx]
return np.array([lm.x, lm.y, lm.z * 0.5]) # z 权重减半
```
### 7.5 与原始规则的对比
| 维度 | 原始规则 | 优化后 |
|------|----------|--------|
| 判断方式 | 硬 if-else(可能冲突/遗漏)| 评分制(必然有结果)|
| 关键点 | 12 个 | 16 个(增加太阳穴、下巴缘点)|
| 特征数 | 5-6 个 | 15 个(含复合特征)|
| 输出 | 单一标签 | 标签 + 置信度 + 混合脸型 |
| 边界处理 | 无 | 三角窗平滑 + 低分兜底 |
| 可调性 | 改阈值需要理解全部分支 | 改 `peak` 值即可微调 |
| 代码行数 | ~60 行 | ~300 行(含注释)|
---
## 八、测试用例参考
```python
# 单元测试伪代码
test_cases = [
# (features_dict, expected_shape)
({'aspect_ratio': 0.92, 'jaw_angle': 148, 'taper_ratio': 0.03,
'chin_sharpness': 0.75, 'width_uniformity': 0.06,
'forehead_ratio': 0.98, 'jaw_ratio': 0.95, 'chin_ratio': 0.70,
'face_curve_score': 0.18, ...}, '圆形脸'),
({'aspect_ratio': 0.77, 'jaw_angle': 135, 'taper_ratio': 0.10,
'chin_sharpness': 0.60, 'width_uniformity': 0.08,
'forehead_ratio': 0.98, 'jaw_ratio': 0.92, 'chin_ratio': 0.62,
'face_curve_score': 0.19, ...}, '鹅蛋脸'),
# ... 更多测试用例
]
```
---
*报告结束。代码可直接集成到 Mediapipe 人脸分析流水线中。*
+874
View File
@@ -0,0 +1,874 @@
"""
face_shape_classifier.py
基于 Mediapipe 468 点人脸关键点的脸型分类系统
支持的脸型圆形脸 / 心形脸 / 菱形脸 / 鹅蛋脸 / 方形脸 / 长形脸 / 瓜子脸
分类策略多维度特征提取 加权评分 置信度判断
实现说明
- 特征与评分框架参考 face_shape_classification.md
- 距离一律在像素坐标系下用 2D 计算归一化坐标未校正宽高比会导致面宽被夸大
- 阈值按 MediaPipe 实测分布做了校准
"""
from __future__ import annotations
import math
from pathlib import Path
from typing import Dict, List, Optional, Tuple, Union
import cv2
import mediapipe as mp
import numpy as np
ImageInput = Union[str, Path, np.ndarray]
class FaceLandmarks:
"""Mediapipe 关键点索引(脸型分析用)。"""
FOREHEAD_TOP = 10
CHIN_BOTTOM = 152
# 额侧(比 127/356 更贴近发际两侧,避免把太阳穴外轮廓算成额头)
LEFT_FOREHEAD = 54
RIGHT_FOREHEAD = 284
# 太阳穴辅助
LEFT_TEMPLE = 21
RIGHT_TEMPLE = 251
# 颧骨最外侧
LEFT_CHEEK = 234
RIGHT_CHEEK = 454
# 下颌角(比 172/397 更接近 gonion
LEFT_JAW_ANGLE = 132
RIGHT_JAW_ANGLE = 361
# 下巴缘
LEFT_CHIN = 136
RIGHT_CHIN = 365
def extract_face_features(landmarks, image_size: Tuple[int, int]) -> Dict[str, float]:
"""
Mediapipe 关键点提取脸型特征
参数:
landmarks: NormalizedLandmark 列表
image_size: (width, height)用于还原像素坐标
"""
w, h = image_size
def pt(idx: int) -> np.ndarray:
lm = landmarks[idx]
return np.array([lm.x * w, lm.y * h], dtype=float)
def dist(p1: np.ndarray, p2: np.ndarray) -> float:
return float(np.linalg.norm(p1 - p2))
def xwidth(p1: np.ndarray, p2: np.ndarray) -> float:
"""横向宽度(脸型比例更稳定)。"""
return abs(float(p1[0] - p2[0]))
forehead_top = pt(FaceLandmarks.FOREHEAD_TOP)
chin_bottom = pt(FaceLandmarks.CHIN_BOTTOM)
left_forehead = pt(FaceLandmarks.LEFT_FOREHEAD)
right_forehead = pt(FaceLandmarks.RIGHT_FOREHEAD)
left_temple = pt(FaceLandmarks.LEFT_TEMPLE)
right_temple = pt(FaceLandmarks.RIGHT_TEMPLE)
left_cheek = pt(FaceLandmarks.LEFT_CHEEK)
right_cheek = pt(FaceLandmarks.RIGHT_CHEEK)
left_jaw = pt(FaceLandmarks.LEFT_JAW_ANGLE)
right_jaw = pt(FaceLandmarks.RIGHT_JAW_ANGLE)
left_chin = pt(FaceLandmarks.LEFT_CHIN)
right_chin = pt(FaceLandmarks.RIGHT_CHIN)
face_height = dist(forehead_top, chin_bottom)
forehead_width = xwidth(left_forehead, right_forehead)
temple_width = xwidth(left_temple, right_temple)
cheekbone_width = xwidth(left_cheek, right_cheek)
jaw_width = xwidth(left_jaw, right_jaw)
chin_width = xwidth(left_chin, right_chin)
face_width = cheekbone_width
eps = 1e-8
# 下巴顶点夹角:越大越宽圆,越小越尖
v_left = left_jaw - chin_bottom
v_right = right_jaw - chin_bottom
cos_val = np.dot(v_left, v_right) / (
np.linalg.norm(v_left) * np.linalg.norm(v_right) + eps
)
cos_val = float(np.clip(cos_val, -1.0, 1.0))
jaw_angle = math.degrees(math.acos(cos_val))
# 下颌角(左):颧骨→下颌角→下巴,越小越方正硬朗
v1 = left_cheek - left_jaw
v2 = chin_bottom - left_jaw
cos_g = np.dot(v1, v2) / (np.linalg.norm(v1) * np.linalg.norm(v2) + eps)
cos_g = float(np.clip(cos_g, -1.0, 1.0))
gonion_angle = math.degrees(math.acos(cos_g))
aspect_ratio = face_width / (face_height + eps)
length_ratio = face_height / (face_width + eps)
taper_ratio = (forehead_width - chin_width) / (forehead_width + eps)
cheek_taper = (cheekbone_width - jaw_width) / (cheekbone_width + eps)
forehead_ratio = forehead_width / (face_width + eps)
temple_ratio = temple_width / (face_width + eps)
jaw_ratio = jaw_width / (face_width + eps)
chin_ratio = chin_width / (face_width + eps)
chin_sharpness = chin_width / (jaw_width + eps)
widths = [forehead_width, cheekbone_width, jaw_width]
width_uniformity = (max(widths) - min(widths)) / (max(widths) + eps)
jaw_midpoint = (left_jaw + right_jaw) / 2.0
face_curve_score = dist(jaw_midpoint, chin_bottom) / (face_height + eps)
forehead_vs_jaw = forehead_width / (jaw_width + eps)
cheek_dominance = cheekbone_width / ((forehead_width + jaw_width) / 2.0 + eps)
return {
"face_height": face_height,
"face_width": face_width,
"forehead_width": forehead_width,
"temple_width": temple_width,
"cheekbone_width": cheekbone_width,
"jaw_width": jaw_width,
"chin_width": chin_width,
"aspect_ratio": aspect_ratio,
"length_ratio": length_ratio,
"taper_ratio": taper_ratio,
"cheek_taper": cheek_taper,
"forehead_ratio": forehead_ratio,
"temple_ratio": temple_ratio,
"cheekbone_ratio": 1.0,
"jaw_ratio": jaw_ratio,
"chin_ratio": chin_ratio,
"jaw_angle": jaw_angle,
"gonion_angle": gonion_angle,
"chin_sharpness": chin_sharpness,
"width_uniformity": width_uniformity,
"face_curve_score": face_curve_score,
"forehead_vs_jaw": forehead_vs_jaw,
"cheek_dominance": cheek_dominance,
}
# ============================================================
# 参考分布:1143 张样本(1093 张脸型测试集合 + 44 张真实照片 + 6 张标注图)
# 的稳健统计量 (中位数, 稳健标准差=IQR/1.349),把绝对测量值转成 z 分数。
# 绝对阈值会随镜头、人群漂移;z 分数让评分只依赖"相对人群偏离多少"。
#
# 早前这组数字只由 50 张样本估得,相对全量人群有系统性偏移
# jaw_ratio 中位偏低 0.44 sd、taper_ratio 偏高 0.53 sd 等),
# 恰好三项都在给方形脸加分,是方形脸占比虚高的主因之一。
# ============================================================
REFERENCE_STATS: Dict[str, Tuple[float, float]] = {
"aspect_ratio": (0.8294, 0.0281),
"jaw_angle": (88.6299, 3.9040),
"gonion_angle": (144.5014, 3.4991),
"taper_ratio": (0.2671, 0.0376),
"forehead_ratio": (0.8975, 0.0204),
"jaw_ratio": (0.9286, 0.0138),
"chin_ratio": (0.6578, 0.0217),
"chin_sharpness": (0.7092, 0.0155),
"width_uniformity": (0.1028, 0.0184),
"forehead_vs_jaw": (0.9669, 0.0341),
"cheek_dominance": (1.0953, 0.0084),
"face_curve_score": (0.3940, 0.0210),
}
# 匹配容差(以 z 为单位):偏离目标 1 个容差,该项得分降到约 0.61
MATCH_TOLERANCE = 1.0
# 每种脸型的原型:特征 -> (目标 z, 权重, 模式)
# 'high' 超过目标即满分(越极端越像)
# 'low' 低于目标即满分
# 'peak' 双侧衰减(该特征应当落在目标附近)
#
# 只使用互相独立的特征:length_ratio(=1/aspect_ratio) 与
# cheek_taper(=1-jaw_ratio) 是重复信号,纳入会让对应脸型拿双倍权重。
#
# 靶心与权重的来源:先按 1093 张测试集中各原始分组(方形脸/长形脸/瓜子脸/
# 标准脸/娃娃脸)的实测 z 画像给出靶心,再在「6 张标注图判定不变」的硬约束下
# 做带边界的退火微调(权重限 [0.5,5]、靶心限 [-2,2],并惩罚失去区分力的空项)。
SHAPE_PROTOTYPES: Dict[str, Dict[str, Tuple[float, float, str]]] = {
# 宽、短,下颌圆钝
"圆形脸": {
"aspect_ratio": (+2.00, 5.00, "high"),
"jaw_angle": (-0.07, 2.28, "high"),
"chin_sharpness": (+0.15, 0.50, "peak"),
"face_curve_score": (+0.17, 3.67, "low"),
},
# 额头宽、下颌与下巴明显收窄
"心形脸": {
"forehead_vs_jaw": (+1.94, 1.62, "high"),
"taper_ratio": (+2.00, 1.09, "high"),
"jaw_ratio": (+1.02, 1.86, "low"),
"chin_ratio": (-1.70, 1.71, "low"),
"aspect_ratio": (+1.69, 1.31, "peak"),
},
# 颧骨最突出,额头与下颌都窄
"菱形脸": {
"cheek_dominance": (+1.62, 2.84, "high"),
"width_uniformity": (+1.24, 2.12, "high"),
"forehead_ratio": (-1.57, 4.58, "low"),
"jaw_ratio": (-0.11, 1.85, "low"),
"aspect_ratio": (+1.31, 2.60, "peak"),
},
# 各项都接近人群中位——没有突出特征即为匀称
"鹅蛋脸": {
"aspect_ratio": (-0.26, 5.00, "peak"),
"jaw_ratio": (+0.45, 2.47, "peak"),
"chin_sharpness": (+0.52, 2.88, "peak"),
"width_uniformity": (+0.53, 0.94, "peak"),
"cheek_dominance": (-0.51, 1.14, "peak"),
},
# 下颌与下巴都宽、几乎不收窄、下颌角锐利、额头相对窄。
# 注意 aspect_ratio 用 peak 而非 high:测试集中 121 张方脸的
# aspect_ratio 中位仅 +0.16,真正"宽"的是娃娃脸(+1.01)——
# 早前把它当成 high 模式的强特征,是方形脸吞掉圆脸的主因。
#
# chin_ratio 是方脸组区分度最大的一项(组内中位 z=+1.45,标准脸组仅 -0.06),
# 故靶心直接对齐 +1.45。靶心与权重必须同时提:若只加权重而把靶心留在低位,
# 全人群八成都能拿满分,等于给所有人同加一笔,反而推高方形脸占比。
"方形脸": {
"aspect_ratio": (+1.11, 4.75, "peak"),
"jaw_ratio": (-0.02, 2.27, "high"),
"chin_ratio": (+1.45, 3.00, "high"),
"taper_ratio": (-0.38, 0.51, "low"),
"chin_sharpness": (-0.38, 0.99, "high"),
"width_uniformity": (+0.58, 4.34, "high"),
"gonion_angle": (+0.10, 3.38, "low"),
"forehead_ratio": (-1.70, 4.05, "low"),
},
# 明显偏长偏窄
"长形脸": {
"aspect_ratio": (-1.49, 1.17, "low"),
"chin_sharpness": (+1.76, 0.50, "high"),
"taper_ratio": (+0.84, 0.50, "low"),
},
# 似心形但下巴更长更尖(face_curve_score 高),颧骨不外扩
"瓜子脸": {
"face_curve_score": (+1.02, 3.41, "high"),
"forehead_ratio": (+0.85, 3.31, "high"),
"taper_ratio": (+0.35, 1.02, "high"),
"cheek_dominance": (-1.41, 2.21, "low"),
"jaw_ratio": (-1.04, 0.57, "low"),
"chin_sharpness": (-1.33, 2.53, "low"),
},
}
def feature_zscores(features: Dict[str, float]) -> Dict[str, float]:
"""把测量值转成相对参考人群的 z 分数。"""
return {
key: (features[key] - median) / scale
for key, (median, scale) in REFERENCE_STATS.items()
if key in features
}
def _match(z: float, target: float, mode: str) -> float:
"""单项匹配度 0~1。"""
if mode == "high" and z >= target:
return 1.0
if mode == "low" and z <= target:
return 1.0
return math.exp(-((z - target) ** 2) / (2 * MATCH_TOLERANCE**2))
def classify_face_shape(
features: Dict[str, float],
return_details: bool = False,
) -> Tuple[str, float, Optional[Dict]]:
"""
脸型分类器把特征转成 z 分数后与各脸型原型做加权匹配
返回 (脸型, 置信度, 详情)置信度 = Top1 / (Top1 + Top2)
0.5 表示两种脸型完全无法区分接近 1 表示判定明确
"""
z = feature_zscores(features)
scores: Dict[str, float] = {}
contributions: Dict[str, Dict[str, float]] = {}
for shape, prototype in SHAPE_PROTOTYPES.items():
total_weight = sum(w for _, w, _ in prototype.values())
acc = 0.0
per_feature = {}
for key, (target, weight, mode) in prototype.items():
m = _match(z[key], target, mode)
per_feature[key] = m
acc += weight * m
scores[shape] = 100.0 * acc / total_weight
contributions[shape] = per_feature
ranked = sorted(scores.items(), key=lambda x: x[1], reverse=True)
best_shape, best_score = ranked[0]
second_shape, second_score = ranked[1] if len(ranked) > 1 else (None, 0.0)
denom = best_score + second_score
confidence = best_score / denom if denom > 0 else 0.0
score_gap = best_score - second_score
is_mixed = score_gap < 5.0
details = None
if return_details:
details = {
"scores": scores,
"ranked": ranked,
"confidence": confidence,
"score_gap": score_gap,
"is_mixed": is_mixed,
"second_shape": second_shape,
"second_score": second_score,
"zscores": z,
"contributions": contributions,
}
return best_shape, confidence, details
def get_mixed_description(details: Dict) -> str:
if not details or not details.get("is_mixed"):
return ""
shape1 = details["ranked"][0][0]
shape2 = details["ranked"][1][0]
return f"{shape1}(偏{shape2}"
_face_mesh = None
def _get_face_mesh():
global _face_mesh
if _face_mesh is None:
_face_mesh = mp.solutions.face_mesh.FaceMesh(
static_image_mode=True,
max_num_faces=1,
refine_landmarks=True,
min_detection_confidence=0.5,
)
return _face_mesh
def _load_image(image: ImageInput) -> np.ndarray:
if isinstance(image, np.ndarray):
if image.ndim != 3 or image.shape[2] not in (3, 4):
raise ValueError("numpy 图片需为 HxWx3/4 的彩色图")
if image.shape[2] == 4:
return cv2.cvtColor(image, cv2.COLOR_BGRA2BGR)
return image
path = Path(image)
img = cv2.imread(str(path))
if img is None:
raise FileNotFoundError(f"无法读取图片: {path}")
return img
def _landmark_points(landmarks, image_size: Tuple[int, int]) -> Dict[str, Tuple[int, int]]:
"""提取标注用像素点。"""
w, h = image_size
def xy(idx: int) -> Tuple[int, int]:
lm = landmarks[idx]
return int(round(lm.x * w)), int(round(lm.y * h))
left_jaw = xy(FaceLandmarks.LEFT_JAW_ANGLE)
right_jaw = xy(FaceLandmarks.RIGHT_JAW_ANGLE)
return {
"forehead_top": xy(FaceLandmarks.FOREHEAD_TOP),
"chin_bottom": xy(FaceLandmarks.CHIN_BOTTOM),
"left_forehead": xy(FaceLandmarks.LEFT_FOREHEAD),
"right_forehead": xy(FaceLandmarks.RIGHT_FOREHEAD),
"left_cheek": xy(FaceLandmarks.LEFT_CHEEK),
"right_cheek": xy(FaceLandmarks.RIGHT_CHEEK),
"left_jaw": left_jaw,
"right_jaw": right_jaw,
"left_chin": xy(FaceLandmarks.LEFT_CHIN),
"right_chin": xy(FaceLandmarks.RIGHT_CHIN),
"jaw_mid": (
int(round((left_jaw[0] + right_jaw[0]) / 2)),
int(round((left_jaw[1] + right_jaw[1]) / 2)),
),
}
def _put_text_cn(
img: np.ndarray,
text: str,
org: Tuple[int, int],
color: Tuple[int, int, int],
font_size: int = 18,
) -> None:
"""在图上绘制中文/英文混合文字(Pillow)。"""
from PIL import Image, ImageDraw, ImageFont
rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
pil = Image.fromarray(rgb)
draw = ImageDraw.Draw(pil)
font_paths = [
"/usr/share/fonts/truetype/wqy/wqy-microhei.ttc",
"/usr/share/fonts/opentype/noto/NotoSansCJK-Regular.ttc",
"/usr/share/fonts/truetype/noto/NotoSansCJK-Regular.ttc",
"/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf",
]
font = None
for fp in font_paths:
if Path(fp).exists():
try:
font = ImageFont.truetype(fp, font_size)
break
except OSError:
continue
if font is None:
font = ImageFont.load_default()
x, y = org
# 阴影提升可读性
draw.text((x + 1, y + 1), text, font=font, fill=(0, 0, 0))
draw.text((x, y), text, font=font, fill=(color[2], color[1], color[0]))
img[:] = cv2.cvtColor(np.array(pil), cv2.COLOR_RGB2BGR)
def _draw_h_line(
img: np.ndarray,
p1: Tuple[int, int],
p2: Tuple[int, int],
color: Tuple[int, int, int],
label: str,
thickness: int = 2,
label_above: bool = True,
) -> None:
"""画横向宽度线 + 端点 + 标签。"""
y = int(round((p1[1] + p2[1]) / 2))
x1, x2 = min(p1[0], p2[0]), max(p1[0], p2[0])
cv2.line(img, (x1, y), (x2, y), color, thickness, cv2.LINE_AA)
cv2.circle(img, (x1, y), 4, color, -1, cv2.LINE_AA)
cv2.circle(img, (x2, y), 4, color, -1, cv2.LINE_AA)
# 端点小竖线
tick = max(6, thickness * 3)
cv2.line(img, (x1, y - tick), (x1, y + tick), color, thickness, cv2.LINE_AA)
cv2.line(img, (x2, y - tick), (x2, y + tick), color, thickness, cv2.LINE_AA)
mid = ((x1 + x2) // 2, y - 8 if label_above else y + 4)
_put_text_cn(img, label, mid, color, font_size=max(14, img.shape[0] // 55))
def _draw_v_line(
img: np.ndarray,
p1: Tuple[int, int],
p2: Tuple[int, int],
color: Tuple[int, int, int],
label: str,
thickness: int = 2,
) -> None:
"""画纵向高度线 + 端点 + 标签。"""
x = int(round((p1[0] + p2[0]) / 2))
y1, y2 = min(p1[1], p2[1]), max(p1[1], p2[1])
cv2.line(img, (x, y1), (x, y2), color, thickness, cv2.LINE_AA)
cv2.circle(img, (x, y1), 4, color, -1, cv2.LINE_AA)
cv2.circle(img, (x, y2), 4, color, -1, cv2.LINE_AA)
tick = max(6, thickness * 3)
cv2.line(img, (x - tick, y1), (x + tick, y1), color, thickness, cv2.LINE_AA)
cv2.line(img, (x - tick, y2), (x + tick, y2), color, thickness, cv2.LINE_AA)
_put_text_cn(
img,
label,
(x + 8, (y1 + y2) // 2),
color,
font_size=max(14, img.shape[0] // 55),
)
def annotate_face_features(
image: ImageInput,
landmarks=None,
features: Optional[Dict[str, float]] = None,
) -> np.ndarray:
"""
在原图上标注 face_width / face_height 及文档中的关键比例特征
返回 BGR 标注图
"""
bgr = _load_image(image).copy()
h, w = bgr.shape[:2]
if landmarks is None:
rgb = cv2.cvtColor(bgr, cv2.COLOR_BGR2RGB)
results = _get_face_mesh().process(rgb)
if not results.multi_face_landmarks:
raise ValueError("未检测到人脸关键点")
landmarks = results.multi_face_landmarks[0].landmark
if features is None:
features = extract_face_features(landmarks, image_size=(w, h))
pts = _landmark_points(landmarks, (w, h))
overlay = bgr.copy()
fs = max(14, h // 55)
thick = max(2, h // 400)
# ---- 尺寸主轴 ----
# face_height: 额头顶 → 下巴底
_draw_v_line(
overlay,
pts["forehead_top"],
pts["chin_bottom"],
(40, 180, 255),
f"face_height {features['face_height']:.0f}px",
thickness=thick + 1,
)
# face_width (= cheekbone): 左颧 → 右颧
_draw_h_line(
overlay,
pts["left_cheek"],
pts["right_cheek"],
(0, 220, 120),
f"face_width {features['face_width']:.0f}px",
thickness=thick + 1,
label_above=True,
)
# ---- 各级宽度(forehead / jaw / chin----
# 略微错开 y,避免完全重叠
fh_y = pts["left_forehead"][1]
_draw_h_line(
overlay,
(pts["left_forehead"][0], fh_y),
(pts["right_forehead"][0], fh_y),
(255, 160, 40),
f"forehead ratio={features['forehead_ratio']:.3f}",
thickness=thick,
label_above=True,
)
jy = pts["left_jaw"][1]
_draw_h_line(
overlay,
(pts["left_jaw"][0], jy),
(pts["right_jaw"][0], jy),
(80, 120, 255),
f"jaw ratio={features['jaw_ratio']:.3f}",
thickness=thick,
label_above=False,
)
cy = pts["left_chin"][1]
_draw_h_line(
overlay,
(pts["left_chin"][0], cy),
(pts["right_chin"][0], cy),
(220, 80, 220),
f"chin ratio={features['chin_ratio']:.3f}",
thickness=thick,
label_above=False,
)
# cheekbone_ratio(相对 face_width,恒为 1.0)写在颧骨线旁
cheek_mid = (
(pts["left_cheek"][0] + pts["right_cheek"][0]) // 2,
pts["left_cheek"][1] + max(18, h // 40),
)
_put_text_cn(
overlay,
f"cheekbone_ratio={features['cheekbone_ratio']:.3f}",
cheek_mid,
(0, 200, 100),
font_size=fs,
)
# ---- jaw_angle:下巴 → 左右下颌角 ----
cv2.line(overlay, pts["chin_bottom"], pts["left_jaw"], (0, 90, 255), thick, cv2.LINE_AA)
cv2.line(overlay, pts["chin_bottom"], pts["right_jaw"], (0, 90, 255), thick, cv2.LINE_AA)
cv2.circle(overlay, pts["chin_bottom"], 5, (0, 90, 255), -1, cv2.LINE_AA)
# 角度弧
v1 = np.array(pts["left_jaw"], dtype=float) - np.array(pts["chin_bottom"], dtype=float)
v2 = np.array(pts["right_jaw"], dtype=float) - np.array(pts["chin_bottom"], dtype=float)
a1 = math.degrees(math.atan2(-v1[1], v1[0]))
a2 = math.degrees(math.atan2(-v2[1], v2[0]))
# OpenCV ellipse 角度:从 x 轴顺时针;atan2 转一下
start_ang = -a1
end_ang = -a2
if end_ang < start_ang:
start_ang, end_ang = end_ang, start_ang
radius = max(28, int(0.08 * features["face_height"]))
cv2.ellipse(
overlay,
pts["chin_bottom"],
(radius, radius),
0,
start_ang,
end_ang,
(0, 90, 255),
thick,
cv2.LINE_AA,
)
_put_text_cn(
overlay,
f"jaw_angle {features['jaw_angle']:.1f}°",
(pts["chin_bottom"][0] + radius + 4, pts["chin_bottom"][1] - radius),
(0, 90, 255),
font_size=fs,
)
# ---- taper_ratio:额头两端 → 下巴两端(收窄示意)----
cv2.line(
overlay,
pts["left_forehead"],
pts["left_chin"],
(40, 200, 255),
max(1, thick - 1),
cv2.LINE_AA,
)
cv2.line(
overlay,
pts["right_forehead"],
pts["right_chin"],
(40, 200, 255),
max(1, thick - 1),
cv2.LINE_AA,
)
taper_anchor = (
pts["left_forehead"][0] - max(10, w // 30),
(pts["left_forehead"][1] + pts["left_chin"][1]) // 2,
)
_put_text_cn(
overlay,
f"taper_ratio={features['taper_ratio']:.3f}",
taper_anchor,
(40, 200, 255),
font_size=fs,
)
# ---- chin_sharpness:下巴宽 vs 下颌宽 ----
_put_text_cn(
overlay,
f"chin_sharpness={features['chin_sharpness']:.3f} (chin/jaw)",
(pts["left_chin"][0], pts["left_chin"][1] + max(16, h // 45)),
(220, 80, 220),
font_size=fs,
)
# ---- width_uniformity:三宽差异 ----
widths = [
("F", features["forehead_width"], (255, 160, 40)),
("C", features["cheekbone_width"], (0, 220, 120)),
("J", features["jaw_width"], (80, 120, 255)),
]
# 右侧小柱状示意
panel_x = min(w - max(90, w // 8), max(pts["right_cheek"][0] + 20, w - max(100, w // 7)))
panel_y = max(40, pts["forehead_top"][1])
max_w = max(x[1] for x in widths) + 1e-8
bar_h = max(10, h // 60)
gap = max(4, h // 120)
for i, (name, val, color) in enumerate(widths):
bw = int((val / max_w) * max(50, w // 10))
y0 = panel_y + i * (bar_h + gap)
cv2.rectangle(overlay, (panel_x, y0), (panel_x + bw, y0 + bar_h), color, -1, cv2.LINE_AA)
_put_text_cn(overlay, name, (panel_x + bw + 4, y0 - 2), color, font_size=max(12, fs - 2))
_put_text_cn(
overlay,
f"width_uniformity={features['width_uniformity']:.3f}",
(panel_x, panel_y + 3 * (bar_h + gap) + 2),
(230, 230, 230),
font_size=fs,
)
# ---- face_curve_score:下颌中点 → 下巴 ----
cv2.line(
overlay,
pts["jaw_mid"],
pts["chin_bottom"],
(180, 255, 80),
thick,
cv2.LINE_AA,
)
cv2.circle(overlay, pts["jaw_mid"], 4, (180, 255, 80), -1, cv2.LINE_AA)
curve_label_pos = (
pts["jaw_mid"][0] + 6,
pts["jaw_mid"][1] - max(8, h // 80),
)
_put_text_cn(
overlay,
f"face_curve_score={features['face_curve_score']:.3f}",
curve_label_pos,
(180, 255, 80),
font_size=fs,
)
# 半透明叠回原图,再叠一层实线标注更清晰:直接用 overlay
# 左侧参数图例
legend = [
("face_width / face_height", (0, 220, 120)),
(f"jaw_angle={features['jaw_angle']:.1f}°", (0, 90, 255)),
(f"taper_ratio={features['taper_ratio']:.3f}", (40, 200, 255)),
(f"forehead_ratio={features['forehead_ratio']:.3f}", (255, 160, 40)),
(f"cheekbone_ratio={features['cheekbone_ratio']:.3f}", (0, 200, 100)),
(f"jaw_ratio={features['jaw_ratio']:.3f}", (80, 120, 255)),
(f"chin_ratio={features['chin_ratio']:.3f}", (220, 80, 220)),
(f"chin_sharpness={features['chin_sharpness']:.3f}", (220, 80, 220)),
(f"width_uniformity={features['width_uniformity']:.3f}", (230, 230, 230)),
(f"face_curve_score={features['face_curve_score']:.3f}", (180, 255, 80)),
]
box_h = 12 + len(legend) * (fs + 6)
box_w = max(220, w // 3)
cv2.rectangle(overlay, (8, 8), (8 + box_w, 8 + box_h), (20, 20, 20), -1)
cv2.rectangle(overlay, (8, 8), (8 + box_w, 8 + box_h), (90, 90, 90), 1)
for i, (text, color) in enumerate(legend):
_put_text_cn(overlay, text, (16, 14 + i * (fs + 6)), color, font_size=fs)
return overlay
def classify_from_image(
image: ImageInput,
return_details: bool = True,
return_annotated: bool = False,
) -> Dict:
"""
从图片判断脸型
参数:
image: 图片路径 OpenCV BGR numpy 数组
return_details: 是否返回特征与各脸型得分
return_annotated: 是否同时返回特征标注图BGR
"""
bgr = _load_image(image)
h, w = bgr.shape[:2]
rgb = cv2.cvtColor(bgr, cv2.COLOR_BGR2RGB)
results = _get_face_mesh().process(rgb)
if not results.multi_face_landmarks:
raise ValueError("未检测到人脸关键点")
landmarks = results.multi_face_landmarks[0].landmark
features = extract_face_features(landmarks, image_size=(w, h))
shape, conf, details = classify_face_shape(features, return_details=True)
display = get_mixed_description(details) or shape
result = {
"face_shape": shape,
"confidence": conf,
"display": display,
}
if return_details:
result["features"] = features
result["details"] = details
if return_annotated:
result["annotated"] = annotate_face_features(
bgr, landmarks=landmarks, features=features
)
return result
def classify_from_mediapipe(
multi_face_landmarks,
image_size: Tuple[int, int],
) -> List[Dict]:
"""从 Mediapipe FaceMesh 结果批量分类。image_size=(width, height)。"""
results = []
for face_lms in multi_face_landmarks:
features = extract_face_features(face_lms.landmark, image_size=image_size)
shape, conf, details = classify_face_shape(features, return_details=True)
results.append(
{
"face_shape": shape,
"confidence": conf,
"display": get_mixed_description(details) or shape,
"features": features,
"details": details,
}
)
return results
def run_test_images(test_dir: Union[str, Path, None] = None) -> List[Dict]:
"""用 test_img 做回归测试;文件名(不含扩展名)为期望脸型。"""
if test_dir is None:
test_dir = Path(__file__).resolve().parent / "test_img"
test_dir = Path(test_dir)
image_paths = sorted(
p
for p in test_dir.iterdir()
if p.suffix.lower() in {".png", ".jpg", ".jpeg", ".webp", ".bmp"}
)
if not image_paths:
raise FileNotFoundError(f"测试目录无图片: {test_dir}")
rows = []
for path in image_paths:
expected = path.stem
try:
result = classify_from_image(path, return_details=True)
predicted = result["face_shape"]
display = result["display"]
conf = result["confidence"]
top3 = result["details"]["ranked"][:3]
ok = predicted == expected
error = None
except Exception as exc: # noqa: BLE001
predicted = display = conf = None
top3 = []
ok = False
error = str(exc)
rows.append(
{
"file": path.name,
"expected": expected,
"predicted": predicted,
"display": display,
"confidence": conf,
"top3": top3,
"correct": ok,
"error": error,
}
)
return rows
def _print_test_report(rows: List[Dict]) -> None:
correct = sum(1 for r in rows if r["correct"])
total = len(rows)
print("=" * 72)
print("脸型分类测试结果")
print("=" * 72)
for r in rows:
status = "" if r["correct"] else ""
if r["error"]:
print(f"{status} {r['file']}")
print(f" 期望: {r['expected']}")
print(f" 错误: {r['error']}")
continue
top3_str = ", ".join(f"{name}:{score:.1f}" for name, score in r["top3"])
print(f"{status} {r['file']}")
print(f" 期望: {r['expected']}")
print(f" 预测: {r['display']} (conf={r['confidence']:.3f})")
print(f" Top3: {top3_str}")
print("-" * 72)
print(f"准确率: {correct}/{total} = {correct / total:.1%}")
print("=" * 72)
if __name__ == "__main__":
import sys
if len(sys.argv) > 1 and sys.argv[1] not in {"--test", "-t"}:
out = classify_from_image(sys.argv[1], return_details=True)
print(f"脸型: {out['display']}")
print(f"置信度: {out['confidence']:.3f}")
print("各脸型得分:")
for name, score in out["details"]["ranked"]:
print(f" {name}: {score:.1f}")
else:
report = run_test_images()
_print_test_report(report)
Binary file not shown.

After

Width:  |  Height:  |  Size: 655 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 658 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 656 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 649 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 650 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 651 KiB

+49 -31
View File
@@ -6,9 +6,9 @@
- 纵向竖线 8 人头最左 + 左脸颊/左眼外/内角/右眼内/外角/右脸颊 + 人头最右
把头宽切 7 七眼段宽数值上下交替 3 / 4带虚线双箭头
人头最左/最右取自耳朵分割外缘看不到耳朵则省略该侧最少 6 5
- 四庭图片左侧数值下两行换行不带 cm带竖向虚线双箭头
- 四庭图片左侧数值( cm)百分比三行换行带竖向虚线双箭头
- 五条横线右侧标名头顶/发际线/眉心/鼻翼下缘/下巴尖
- 单位 cm 统一标在底部单位cm
- 每段数值直接带 cm 后缀下方另起一行标百分比不再单独标底部单位cm
中文字体用打包的思源黑体绝对路径加载缺字体直接抛错不静默降级成方块
"""
import os
@@ -189,9 +189,8 @@ def create_annotated_image(image_bgr, measure_result, ear_mask=None, hair_mask=N
取自耳朵分割掩膜的外缘方案 BBiSeNet 7/8耳朵不可见被头发/侧脸
遮挡 掩膜空或无掩膜时省略该侧端线只画对应脸颊线
- 横向 5 条分界线头顶/发际线/眉心/鼻翼下缘/下巴尖右侧标名
- 四庭///下庭在左侧 + 数值两行换行 cm竖向虚线双箭头
- 七眼段宽数值上下交替 3 / 4 cm横向虚线双箭头
- 底部统一标单位cm
- 四庭///下庭在左侧 + 数值( cm) + 百分比三行换行竖向虚线双箭头
- 七眼段宽上下交替 3 / 4数值( cm) 百分比占头宽比横向虚线双箭头
variant="v6"接口6去掉头顶横线与顶庭只画发际线/眉心/鼻翼下缘/下巴尖 4
横线 + //下庭竖线纵向范围改为发际线下巴尖且不画人头最左/最右端线
@@ -203,7 +202,7 @@ def create_annotated_image(image_bgr, measure_result, ear_mask=None, hair_mask=N
# --- 自适应尺寸:字号/线宽/虚线/箭头按短边缩放 ---
s = min(w, h)
font_size = max(11, round(s * 0.026)) # 字体更小
font_size = max(9, round(s * 0.020)) # 字号上调一档
line_w = max(1, round(s * 0.0022))
dash_len = max(4, round(s * 0.008))
gap_len = max(2, round(dash_len * 0.7)) # 虚线更稠密(间隙<划线)
@@ -213,7 +212,11 @@ def create_annotated_image(image_bgr, measure_result, ear_mask=None, hair_mask=N
buf = np.zeros((h, w, 4), dtype=np.uint8)
if variant == "v6":
# 发际线弃用(hairline_discarded):保留头顶横线,去掉发际线横线,
# 也不标顶/上庭(缺发际线作边界,算不出)。横线 = 头顶/眉心/鼻翼下缘/下巴尖。
if getattr(measure_result, "hairline_discarded", False):
order = ["hair_top", "brow_center", "nose_bottom", "chin_tip"]
elif variant == "v6":
order = ["hairline", "brow_center", "nose_bottom", "chin_tip"]
else:
order = ["hair_top", "hairline", "brow_center", "nose_bottom", "chin_tip"]
@@ -240,7 +243,7 @@ def create_annotated_image(image_bgr, measure_result, ear_mask=None, hair_mask=N
face_cx = (fx0 + fx1) / 2
over = max(6, round(s * 0.030)) # 线超出包围盒的长度(参考图风格)
face_half = (fx1 - fx0) / 2 + over # 横线超出最外侧竖线一点
# v6 竖线纵向范围 = 发际线→下巴尖(不超出);v1 = 头顶→下巴尖并两端超出一点
# 竖线纵向范围v6 = 发际线→下巴尖(不超出);v1(含发际线弃用)= 头顶→下巴尖并两端超出一点
v_top = fy0 if variant == "v6" else fy0 - over
v_bot = fy1 if variant == "v6" else fy1 + over
@@ -256,70 +259,85 @@ def create_annotated_image(image_bgr, measure_result, ear_mask=None, hair_mask=N
draw = ImageDraw.Draw(canvas)
font = _load_font(font_size)
# --- 3a. 横线右侧:线名(头顶/发际线/眉心/鼻翼下缘/下巴尖),文字在线上方 ---
name_x = fx1 + pad
name_gap = max(2, round(pad * 1.6)) # 文字底部到线的间距(再上移)
# --- 3a. 横线右侧:线名(头顶/发际线/眉心/鼻翼下缘/下巴尖),文字纵向居中对齐到线 ---
name_x = fx1 + over + pad # 移到横线右端外侧一点(往右)
for i, name in enumerate(order):
text = _LINE_NAMES[name]
tw, th = _text_size(draw, text, font)
tw, _ = _text_size(draw, text, font)
x = min(name_x, w - 2 - tw) # 右侧越界时回收
draw.text((x, max(2, ys[i] - th - name_gap)), text, fill=LINE_COLOR, font=font)
# anchor="lm"x 为左、y 为竖直中点 → 文字中线正好压在横线上(与线对齐)
draw.text((x, ys[i]), text, fill=LINE_COLOR, font=font, anchor="lm")
# --- 3b. 左侧四庭:名 + 数值两行(无 cm)+ 竖向虚线双箭头 ---
if variant == "v6":
# court_start:庭段在 order 里的起始索引。发际线弃用时 order 首位是头顶(无下界发际线,
# 顶/上庭不标),中庭从眉心开始 → 跳过 order[0]。
if getattr(measure_result, "hairline_discarded", False):
court_cm = [measure_result.middle_cm, measure_result.lower_cm]
court_name = ["中庭", "下庭"]
n_court = 2
court_start = 1
elif variant == "v6":
court_cm = [measure_result.upper_cm, measure_result.middle_cm, measure_result.lower_cm]
court_name = ["上庭", "中庭", "下庭"]
n_court = 3
court_start = 0
else:
court_cm = [measure_result.top_cm, measure_result.upper_cm,
measure_result.middle_cm, measure_result.lower_cm]
court_name = ["顶庭", "上庭", "中庭", "下庭"]
n_court = 4
court_start = 0
arrow_x = max(arrow_size + 1, fx0 - pad) # 竖箭头所在 x(脸左侧,贴近最左竖线)
court_total = sum(court_cm) or 1.0 # 各庭占比分母 = 四庭(v6 三庭)之和
for i in range(n_court):
y_a, y_b = ys[i], ys[i + 1]
y_a, y_b = ys[court_start + i], ys[court_start + i + 1]
# 竖向虚线双箭头,覆盖该庭高度(略收一点避免压到横线)
inset = min(arrow_size, (y_b - y_a) * 0.12)
draw_dashed_line_with_arrows(
draw, arrow_x, y_a + inset, arrow_x, y_b - inset,
dash_len=dash_len, gap_len=gap_len, arrow_size=arrow_size, width=line_w)
# 名 + 数值行,右对齐到箭头左侧
# 名 + 数值(带 cm) + 百分比三行,右对齐到箭头左侧
name = court_name[i]
val = f"{court_cm[i]:.2f}"
val = f"{court_cm[i]:.2f}cm"
pct = f"{court_cm[i] / court_total * 100:.1f}%"
nw, _ = _text_size(draw, name, font)
vw, _ = _text_size(draw, val, font)
pw, _ = _text_size(draw, pct, font)
label_right = arrow_x - pad
y_mid = (y_a + y_b) / 2
y_top = y_mid - line_h
y_top = y_mid - 1.5 * line_h
draw.text((max(2, label_right - nw), y_top), name, fill=LINE_COLOR, font=font)
draw.text((max(2, label_right - vw), y_top + line_h), val, fill=LINE_COLOR, font=font)
draw.text((max(2, label_right - pw), y_top + 2 * line_h), pct, fill=LINE_COLOR, font=font)
# --- 4. 七眼每段宽度:上下交替(上 3 / 下 4),横向虚线双箭头 + 数值(无 cm ---
# 文字与箭头间留更大间距,避免文字压住箭头
# --- 4. 七眼每段宽度:上下交替(上 3 / 下 4),横向虚线双箭头 + 数值(带 cm) + 百分比 ---
# 每段两行:数值(带 cm) 上、百分比 下;百分比分母 = 整个头宽(七段之和)
txt_off = arrow_size + pad * 2
y_arrow_top = max(txt_off + font_size + 2, fy0 - pad - arrow_size)
y_arrow_bot = min(h - txt_off - font_size - 2, fy1 + pad + arrow_size)
txt_block = 2 * line_h # 两行文字总高(数值 + 百分比)
y_arrow_top = max(txt_off + txt_block + 2, fy0 - pad - arrow_size)
y_arrow_bot = min(h - txt_off - txt_block - 2, fy1 + pad + arrow_size)
head_w = (xs[-1] - xs[0]) or 1.0 # 头宽(像素)= 百分比分母
for i in range(len(xs) - 1):
x_a, x_b = xs[i], xs[i + 1]
if x_b - x_a < 1:
continue
seg_cm = (x_b - x_a) / pc
seg_pct = (x_b - x_a) / head_w * 100
cx_seg = (x_a + x_b) / 2
text = f"{seg_cm:.2f}"
tw, th = _text_size(draw, text, font)
val = f"{seg_cm:.2f}cm"
pct = f"{seg_pct:.1f}%"
vw, _ = _text_size(draw, val, font)
pw, _ = _text_size(draw, pct, font)
inset = min(arrow_size, (x_b - x_a) * 0.12)
on_top = (i % 2 == 1) # 奇数段在上 → 上 3 / 下 4
y_arrow = y_arrow_top if on_top else y_arrow_bot
draw_dashed_line_with_arrows(
draw, x_a + inset, y_arrow, x_b - inset, y_arrow,
dash_len=dash_len, gap_len=gap_len, arrow_size=arrow_size, width=line_w)
ty = (y_arrow - th - txt_off) if on_top else (y_arrow + txt_off)
draw.text((cx_seg - tw / 2, ty), text, fill=LINE_COLOR, font=font)
# --- 5. 底部统一单位 ---
unit = "单位cm"
uw, uh = _text_size(draw, unit, font)
draw.text(((w - uw) / 2, h - uh - max(2, pad)), unit, fill=LINE_COLOR, font=font)
# 数值行在上、百分比行在下;on_top 时整块置于箭头上方,否则下方
text_top = (y_arrow - txt_off - txt_block) if on_top else (y_arrow + txt_off)
draw.text((cx_seg - vw / 2, text_top), val, fill=LINE_COLOR, font=font)
draw.text((cx_seg - pw / 2, text_top + line_h), pct, fill=LINE_COLOR, font=font)
return canvas
+2
View File
@@ -18,6 +18,8 @@ RIGHT_EYE_INNER = 362 # 右眼内角
RIGHT_EYE_OUTER = 263 # 右眼外角
LEFT_CHEEK = 234 # 左脸颧弓(脸宽左端)
RIGHT_CHEEK = 454 # 右脸颧弓(脸宽右端)
LEFT_POSITION = 21 # 左脸前侧定位点(脸颊/耳前区域,与 251 镜像)
RIGHT_POSITION = 251 # 右脸前侧定位点(与 21 镜像)
# --- 鼻尖(solvePnP 用,可选) ---
NOSE_TIP = 1 # 鼻尖(也有用 4 的版本)
+459 -83
View File
@@ -35,6 +35,7 @@ from face_analysis.detector import detector
from face_analysis.calibration import estimate_scale_factor
from face_analysis.head_mask import (
NoFaceError,
BASELINE_IDX,
_baseline_points,
_upper_region_mask,
_bisenet_hair_mask,
@@ -46,8 +47,11 @@ from face_analysis.head_mask import (
_draw_baseline,
)
# 调试日志:写 /home/xsl/hair/log/hairline_grow.log,每个步骤详细记录
_LOG_DIR = "/home/xsl/hair/log"
# 调试日志:写 <仓库根>/log/hairline_grow.log,每个步骤详细记录(可用 HAIR_LOG_DIR 覆盖)
_LOG_DIR = os.getenv(
"HAIR_LOG_DIR",
os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "log"),
)
os.makedirs(_LOG_DIR, exist_ok=True)
logger = logging.getLogger("hairline_grow")
_log_fh = logging.FileHandler(os.path.join(_LOG_DIR, "hairline_grow.log"), encoding="utf-8")
@@ -60,6 +64,10 @@ SWAP_URL = os.getenv("SWAP_HAIR_URL", "http://127.0.0.1:8801/api/swapHair/v1")
HAIRGROW_URL = os.getenv("HAIR_GROW_URL", "http://127.0.0.1:8801/api/hairGrow/v1")
SWAP_TIMEOUT = float(os.getenv("SWAP_HAIR_TIMEOUT", "300"))
# 多频段融合最细层羽化:羽化最细 FEATHER_LAYERS 层(每层核尺寸按尺度放大)。
# 只羽最细1层效果极弱(其拉普拉斯系数幅度小),羽化 3 层才能明显软化发丝边缘锯齿。
FEATHER_LAYERS = 3
DEFAULTS = {
"gen_backend": "swaphair", # swaphair(换发型LoRA) | hairgrow(区域生发inpaint)
"is_hr": False,
@@ -94,11 +102,26 @@ def _png_b64(bgr_or_gray):
def _gray_b64(gray_float):
"""0~1 的浮图 → 灰度 PNG data URI。"""
"""0~1 的浮图 → 灰度 PNG data URI。"""
g = np.clip(gray_float * 255.0, 0, 255).astype(np.uint8)
return _png_b64(g)
def _red_mask_b64(mask_bool, h, w):
"""布尔遮罩 → 纯红 alpha PNG data URI。
遮罩区域 RGBA=(255,0,0,255)其余区域 RGBA=(0,0,0,0)
ComfyUI 重绘接口/api/v1/redraw alpha 通道识别重绘区
注意cv2.imencode PNG 用的是 **BGRA** 顺序B,G,R,A所以要得到
浏览器显示的红色 R=255需赋值 (B=0,G=0,R=255,A=255)
"""
m = (mask_bool.astype(np.uint8)) * 255 if mask_bool is not None else np.zeros((h, w), np.uint8)
rgba = np.zeros((h, w, 4), np.uint8)
rgba[m > 0] = (0, 0, 255, 255) # BGRA: B=0,G=0,R=255 → PNG 读出为红色 + 不透明
ok, buf = cv2.imencode(".png", rgba)
return "data:image/png;base64," + base64.b64encode(buf.tobytes()).decode() if ok else ""
# ---------------------------------------------------------------------------
# 步骤1:接口9 头发遮罩(复用 head_mask 构件)
# ---------------------------------------------------------------------------
@@ -294,8 +317,48 @@ def _pushed_mask(hair_mask, upper, baseline_pts, push_px, rid="",
def _redraw_band_mask(inner_pts, outer_pts, h, w, rid="", upper=None,
lo_mult=0.5, hi_mult=1.5):
"""重绘带遮罩:由发际线(①-f 内轮廓 inner_pts)沿径向外推方向,取
`lo_mult × push` `hi_mult × push` 两条外推线之间的带状区域作为重绘 mask
inner_pts / outer_pts 是一一对应的有序点列outer = inner 径向外推 1.0×push_px
故每点的 1.0× 位移向量 = outer - inner下界线 = inner + lo_mult×位移
上界线 = inner + hi_mult×位移闭合环 = 下界线正向+ 上界线反向首尾相接
lo_mult / hi_mult外推倍率相对 hairline_push_cm默认 0.5 / 1.5即带位于
0.5×push ~ 1.5×push 之间以内轮廓为 0×原外推线为 1.0×
upper-a baseline 以上区域布尔掩码传入时把重绘带与它求交集只保留 baseline
以上的部分两侧鬓角落到 baseline 以下的段会被截掉
返回 band_bool
"""
lg = lambda msg: logger.info("[%s] %s", rid, msg) if rid else None
if len(inner_pts) < 2 or len(outer_pts) < 2:
return np.zeros((h, w), dtype=bool)
inner_f = np.asarray(inner_pts, dtype=np.float32)
outer_f = np.asarray(outer_pts, dtype=np.float32)
disp = outer_f - inner_f # 每点 1.0×push 的径向位移向量
lo_line = inner_f + float(lo_mult) * disp # 下界外推线(lo_mult×push
hi_line = inner_f + float(hi_mult) * disp # 上界外推线(hi_mult×push
# 闭合多边形:下界线正向 + 上界线反向,端点自然相连
ring = np.vstack([lo_line.astype(np.int32), hi_line[::-1].astype(np.int32)])
band_u8 = np.zeros((h, w), dtype=np.uint8)
cv2.fillPoly(band_u8, [ring], 255)
band = band_u8 > 0
raw_px = int(band.sum())
# ①-a baseline 截断:只保留 baseline 以上的重绘带
if upper is not None:
band = band & upper
lg(f"_redraw_band_mask: 内轮廓点={len(inner_pts)} lo_mult={lo_mult} hi_mult={hi_mult} "
f"band像素(截断前)={raw_px} band像素(截断后)={int(band.sum())}")
return band
def compute_mask(image_bgr, landmarks, seg_model, mask_type, erode_cm, px_per_cm,
hairline_push_cm=0.0, hairline_edge="column", rid=""):
hairline_push_cm=0.0, hairline_edge="column", rid="", render_viz=True,
hair_mask=None):
"""算出布尔遮罩 + 可视化。
seg_model: bisenet | segformer
@@ -303,6 +366,10 @@ def compute_mask(image_bgr, landmarks, seg_model, mask_type, erode_cm, px_per_cm
hairline_push_cm: pushed 模式发际线往头发方向外推的厘米数进入现有头发
hairline_edge: pushed 模式发际线提取方式 column(逐列最低点) | contour(形态学轮廓)
rid: 调用方的 request id用于日志关联
render_viz: 是否生成各阶段叠图 overlay JPG接口11 调试页用接口2/12 路径传 False
可跳过 6+ base64 编码 ~80ms数据字段_inner_pts/_outer_pts/_upper_mask/
mask_pixels 始终返回不受影响
hair_mask: 预计算的头发布尔遮罩来自 SegFormer parse传入时跳过重复分割 ~0.9s
返回 (mask_bool, viz_dict)
"""
lg = lambda msg: logger.info("[%s] %s", rid, msg) if rid else None
@@ -316,13 +383,16 @@ def compute_mask(image_bgr, landmarks, seg_model, mask_type, erode_cm, px_per_cm
upper = _upper_region_mask(baseline_pts, w, h)
lg(f"baseline 第一点={baseline_pts[0]} 末点={baseline_pts[-1]} upper像素={int(upper.sum())}")
if seg_model == "bisenet":
hair_mask = _bisenet_hair_mask(image_bgr, landmarks, w, h)
elif seg_model == "segformer":
hair_mask = _segformer_hair_mask(image_bgr)
if hair_mask is None:
if seg_model == "bisenet":
hair_mask = _bisenet_hair_mask(image_bgr, landmarks, w, h)
elif seg_model == "segformer":
hair_mask = _segformer_hair_mask(image_bgr)
else:
raise ValueError(f"未知 seg_model: {seg_model}")
lg(f"头发分割完成 seg_model={seg_model} hair_pixels={int(hair_mask.sum())}")
else:
raise ValueError(f"未知 seg_model: {seg_model}")
lg(f"头发分割完成 seg_model={seg_model} hair_pixels={int(hair_mask.sum())}")
lg(f"头发分割跳过(复用外部传入) hair_pixels={int(hair_mask.sum())}")
top_fill = _fill_to_baseline(hair_mask, upper) # 含额头,延伸到图底
closed = _largest_cc(top_fill & upper) # 闭合区域:头发+额头,底=基线
@@ -334,7 +404,9 @@ def compute_mask(image_bgr, landmarks, seg_model, mask_type, erode_cm, px_per_cm
if mask_type == "pushed":
push_px = int(round(max(0.0, hairline_push_cm) * px_per_cm))
# 圆心 = 151 点(眉心)完整坐标,内侧判定与径向外推共用
center = baseline_pts[5] if len(baseline_pts) > 5 else None
# 按值查 151 在 BASELINE_IDX 中的位置,避免列表变动后索引错位(曾硬编码 [5])
_idx151 = BASELINE_IDX.index(151) if 151 in BASELINE_IDX else -1
center = baseline_pts[_idx151] if _idx151 >= 0 else None
# 下颌截断线:下巴关键点 152 的 y(内轮廓两侧向下画到这里为止)
try:
chin_y = int(round(landmarks.landmark[152].y * h))
@@ -361,48 +433,55 @@ def compute_mask(image_bgr, landmarks, seg_model, mask_type, erode_cm, px_per_cm
# 遮罩计算过程可视化:
# eroded/closed 走 top_fill→closed/eroded 流程;
# pushed 走 baseline→头发分割→发际线→外推 流程,与 top_fill/closed 无关,故置空。
# render_viz=False(接口2/12 路径)时跳过 overlay JPG 编码,只保留数据字段。
viz = {
"erode_px": r,
"hair_pixels": int(hair_mask.sum()),
"closed_pixels": int(closed.sum()),
"mask_pixels": int(mask_bool.sum()),
# 1. 发际线分割线(baseline):151 中心点标红,其余点标绿,黄线含左右延长线
"baseline_overlay_base64": _jpg_b64(_draw_baseline(image_bgr, baseline_pts, w)),
"baseline_overlay_base64": _jpg_b64(_draw_baseline(image_bgr, baseline_pts, w)) if render_viz else "",
# 2. 分割线以上区域(upper 半区):青色叠加
"upper_overlay_base64": _jpg_b64(_overlay(image_bgr, upper, (0, 255, 255))),
"upper_overlay_base64": _jpg_b64(_overlay(image_bgr, upper, (0, 255, 255))) if render_viz else "",
# 3. 头发分割原始结果(hair_mask):绿色叠加在原图上
"hair_seg_overlay_base64": _jpg_b64(_overlay(image_bgr, hair_mask, (0, 255, 0))),
"hair_seg_overlay_base64": _jpg_b64(_overlay(image_bgr, hair_mask, (0, 255, 0))) if render_viz else "",
# 4. top_fill / closed —— 仅 eroded/closed 流程用;pushed 流程无关,留空
"top_fill_overlay_base64": "" if mask_type == "pushed"
"top_fill_overlay_base64": "" if (mask_type == "pushed" or not render_viz)
else _jpg_b64(_overlay(image_bgr, top_fill, (255, 0, 0))),
"closed_overlay_base64": "" if mask_type == "pushed"
"closed_overlay_base64": "" if (mask_type == "pushed" or not render_viz)
else _jpg_b64(_overlay(image_bgr, closed, (255, 0, 255))),
# 5. pushed 模式专有(发际线提取/外推)—— 非 pushed 留空
"hairline_overlay_base64": "",
"pushed_overlay_base64": "",
# —— 最终遮罩 ——
"mask_overlay_base64": _jpg_b64(_overlay(image_bgr, mask_bool, (0, 0, 255))),
"mask_base64": _png_b64((mask_bool.astype(np.uint8)) * 255),
"mask_overlay_base64": _jpg_b64(_overlay(image_bgr, mask_bool, (0, 0, 255))) if render_viz else "",
"mask_base64": _png_b64((mask_bool.astype(np.uint8)) * 255) if render_viz else "",
}
# pushed 模式:补充内轮廓提取 + 外推线可视化
if pushed_info is not None:
inner_pts, outer_pts, push_px = pushed_info
# ①-f 提取内轮廓:绿=头发内轮廓线(额头弧+两侧到下颌),黄=baseline 折线
hl_img = _draw_baseline(image_bgr, baseline_pts, w) # 画 baseline(黄线+关键点)
hl_img = _draw_polyline(hl_img, inner_pts, (0, 255, 0), 3)
viz["hairline_overlay_base64"] = _jpg_b64(hl_img)
# ①-g 外推:圆心红点(151) + 内轮廓(绿)+ 外推线(青)+ 遮罩(红半透明)
ps_img = _draw_polyline(image_bgr.copy(), inner_pts, (0, 255, 0), 2)
ps_img = _draw_polyline(ps_img, outer_pts, (0, 255, 255), 3)
# 画圆心(151 点)红点,标示径向外推的中心
if baseline_pts is not None and len(baseline_pts) > 5:
cx151, cy151 = baseline_pts[5]
cv2.circle(ps_img, (cx151, cy151), 6, (0, 0, 255), -1, cv2.LINE_AA)
cv2.putText(ps_img, "151", (cx151 + 8, cy151 - 8),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 1, cv2.LINE_AA)
ps_img = _overlay(ps_img, mask_bool, (0, 0, 255), 0.3)
viz["pushed_overlay_base64"] = _jpg_b64(ps_img)
if render_viz:
# ①-f 提取内轮廓:绿=头发内轮廓线(额头弧+两侧到下颌),黄=baseline 折线
hl_img = _draw_baseline(image_bgr, baseline_pts, w) # 画 baseline(黄线+关键点)
hl_img = _draw_polyline(hl_img, inner_pts, (0, 255, 0), 3)
viz["hairline_overlay_base64"] = _jpg_b64(hl_img)
# ①-g 外推:圆心红点(151) + 内轮廓(绿)+ 外推线(青)+ 遮罩(红半透明)
ps_img = _draw_polyline(image_bgr.copy(), inner_pts, (0, 255, 0), 2)
ps_img = _draw_polyline(ps_img, outer_pts, (0, 255, 255), 3)
# 画圆心(151 点)红点,标示径向外推的中心(_idx151 上方已按值查到)
if center is not None:
cx151, cy151 = center
cv2.circle(ps_img, (cx151, cy151), 6, (0, 0, 255), -1, cv2.LINE_AA)
cv2.putText(ps_img, "151", (cx151 + 8, cy151 - 8),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 1, cv2.LINE_AA)
ps_img = _overlay(ps_img, mask_bool, (0, 0, 255), 0.3)
viz["pushed_overlay_base64"] = _jpg_b64(ps_img)
viz["push_px"] = push_px
# 重绘带用原始数据:内轮廓点 + 外推点(供 _redraw_band_mask 连端点成带)
viz["_inner_pts"] = inner_pts
viz["_outer_pts"] = outer_pts
# baseline 以上区域,供重绘带按 ①-a baseline 截断(只留上面)
viz["_upper_mask"] = upper
# 记录 viz 各字段是否非空(长度),便于排查前端取不到图的问题
viz_summary = {k: (len(v) if isinstance(v, str) and v else 0)
for k, v in viz.items() if k.endswith("_base64")}
@@ -410,15 +489,33 @@ def compute_mask(image_bgr, landmarks, seg_model, mask_type, erode_cm, px_per_cm
return mask_bool, viz
def _segment_hair(image_bgr, seg_model, landmarks, w, h):
"""对任意图(如 hard_paste 重绘结果)重跑头发分割,返回 bool 掩码。
compute_mask 内部用的同一个 seg_model 逻辑bisenet landmarks
segformer 不需要保证第1步原图头发与第2步重绘后头发分割口径一致
"""
if seg_model == "bisenet":
return _bisenet_hair_mask(image_bgr, landmarks, w, h)
elif seg_model == "segformer":
return _segformer_hair_mask(image_bgr)
else:
raise ValueError(f"未知 seg_model: {seg_model}")
# ---------------------------------------------------------------------------
# 步骤2:调 change_hair 换发型
# ---------------------------------------------------------------------------
def _call_swap(image_bgr, hairline_id, is_hr, ext_mask_bool, denoising_strength):
def _call_swap(image_bgr, hairline_id, is_hr, ext_mask_bool, denoising_strength,
inpainting_fill=1, mask_blur=11, mask_dilate_scale=1.0, webui_steps=None):
"""调 change_hair /api/swapHair/v1,返回与输入同分辨率同对齐的换发型结果(BGR)。
ext_mask_bool None 时作为 ext_mask 传入swap_mode=ext_mask
denoising_strengthwebui img2img 重绘强度越大生发越激进透传给换发型
inpainting_fill / mask_blur / mask_dilate_scale服务端重绘参数透传给 change_hair
默认值=服务端原始硬编码值未传时行为不变详见 change_hair 文档
webui_stepswebui img2img 采样步数None 用服务端默认(15)
"""
import requests
@@ -430,7 +527,12 @@ def _call_swap(image_bgr, hairline_id, is_hr, ext_mask_bool, denoising_strength)
"user_img_path": "data:image/jpeg;base64," + base64.b64encode(ibuf.tobytes()).decode(),
"output_format": "base64",
"denoising_strength": float(denoising_strength),
"inpainting_fill": int(inpainting_fill),
"mask_blur": int(mask_blur),
"mask_dilate_scale": float(mask_dilate_scale),
}
if webui_steps is not None:
payload["webui_steps"] = int(webui_steps)
if ext_mask_bool is not None:
mbuf = cv2.imencode(".png", (ext_mask_bool.astype(np.uint8)) * 255)[1]
payload["ext_mask"] = "data:image/png;base64," + base64.b64encode(mbuf.tobytes()).decode()
@@ -500,25 +602,60 @@ def _call_hairgrow(image_bgr, mask_bool, strength):
return result
_REPAINT_WORKFLOW = os.path.join(os.path.dirname(os.path.dirname(__file__)), "hair_repaint.json")
def _call_comfyui(image_bgr, mask_bool, prompt=None):
"""调远端 ComfyUI 的 Flux-2 inpaint 工作流(hair_repaint.json),返回与输入同分辨率的 BGR。
swapHair 的区别ComfyUI 原图 VAE 编码作 reference latent + ColorMatch双重保色
天生不易染色提示词自由可调中文mask RGBA alpha 通道传入透明=重绘区
ComfyUI 不在线时抛 SwapError由调用方捕获降级prompt=None 用工作流内置默认提示词
"""
import io
from hairline.mask import compose_comfy_rgba
from hairline.comfyui import COMFYUI_URL, run as comfyui_run, ping
if not ping():
raise SwapError(f"ComfyUI 不可达({COMFYUI_URL}),redraw Flux-2 路跳过")
mask_u8 = (mask_bool.astype(np.uint8)) * 255
rgba_img = compose_comfy_rgba(image_bgr, mask_u8) # alpha=255-mask:透明=重绘区
buf = io.BytesIO()
rgba_img.save(buf, format="PNG")
png_bytes = comfyui_run(buf.getvalue(), prompt=prompt, workflow_path=_REPAINT_WORKFLOW)
result = cv2.imdecode(np.frombuffer(png_bytes, np.uint8), cv2.IMREAD_COLOR)
if result is None:
raise SwapError("ComfyUI 结果解码失败")
if result.shape[:2] != image_bgr.shape[:2]:
result = cv2.resize(result, (image_bgr.shape[1], image_bgr.shape[0]),
interpolation=cv2.INTER_LANCZOS4)
return result
# ---------------------------------------------------------------------------
# 步骤3+4:按遮罩贴回 + 接缝融合
# ---------------------------------------------------------------------------
def _color_match_to_orig(swap_result, orig, mask_bool):
def _color_match_to_orig(swap_result, orig, mask_bool, strength=1.0):
"""在 mask_bool 区域内做 Reinhard 颜色迁移:逐通道把 swap_result 的均值/方差对齐 orig。
strength 控制迁移强度1.0=完全对齐到 orig原行为<1.0 只迁移部分
防止 Reinhard 在某些图上过度改色如把生成发色整体拉向皮肤色
遮罩外保持 swap_result 原样不会越界污染返回 uint8 BGR
"""
m = mask_bool.astype(bool)
out = swap_result.astype(np.float32).copy()
src_f = swap_result.astype(np.float32)
out = src_f.copy()
if m.sum() < 30:
return swap_result.copy()
strength = float(min(max(strength, 0.0), 1.0))
for c in range(3):
src_pix = swap_result[..., c][m].astype(np.float32)
dst_pix = orig[..., c][m].astype(np.float32)
s_mean, s_std = src_pix.mean(), src_pix.std() + 1e-6
d_mean, d_std = dst_pix.mean(), dst_pix.std() + 1e-6
out[..., c] = (out[..., c] - s_mean) * (d_std / s_std) + d_mean
aligned = (out[..., c] - s_mean) * (d_std / s_std) + d_mean
out[..., c] = src_f[..., c] * (1.0 - strength) + aligned * strength
return np.clip(out, 0, 255).astype(np.uint8)
@@ -553,10 +690,17 @@ def _multiband_alpha(mask_bool, edge_erode_px):
return m
def _multiband_blend(orig, swap_result, mask_bool, levels, edge_erode_px):
def _multiband_blend(orig, swap_result, mask_bool, levels, edge_erode_px,
feather_px=1, transition_band_px=-1):
"""多频段(拉普拉斯金字塔)融合:低频用宽窗抹色差,高频用窄窗保发丝。
levels金字塔层数2~6越大则低频色差在越宽范围被抹平
feather_px最细若干层掩码轻羽化像素0=不羽化保持硬二值羽化最细 FEATHER_LAYERS
核尺寸按层尺度放大消除发丝边缘 1px 硬切锯齿粗层仍保持二值否则粗层会
把整图混色注意这是消除锯齿的微调幅度有限边界 Δ 1~3/255
不要指望它做大范围过渡那是 mb_levels/transition_band_px 的事
transition_band_pxkeep-region 外缘边距-1=自动按层数 2**n旧行为
>=0 则用绝对像素使过渡带宽度与金字塔层数解耦
返回 uint8 BGR
"""
m = _multiband_alpha(mask_bool, edge_erode_px)
@@ -601,6 +745,21 @@ def _multiband_blend(orig, swap_result, mask_bool, levels, edge_erode_px):
lb = lap_pyr(swap_result, n)
ma = mask_pyr(m, n)
# 最细层(reversed 后末元素 = 全分辨率原始二值掩码)及其下若干层轻羽化,
# 消除发丝边缘 1px 硬切锯齿。注意:多频段融合中各层都贡献边界过渡,但最细层的
# 拉普拉斯系数幅度最小,只羽化它效果很弱(实测边界 Δ 仅 ~0.25/255)。因此对最细
# FEATHER_LAYERS 层都做按尺度放大的羽化(越细的层核越大),才能明显软化边缘。
# 粗层(低频)仍保持二值,否则会把整图混色,违反多频段融合的二值掩码前提。
fp = int(max(0, feather_px))
if fp > 0:
for li in range(1, FEATHER_LAYERS + 1):
idx = -li
if abs(idx) > len(ma):
break
scale = 2 ** (li - 1)
ksz = fp * 2 * scale + 1
ma[idx] = cv2.GaussianBlur(ma[idx], (ksz, ksz), sigmaX=fp * scale / 2.0)
merged = []
for a, b, mk in zip(la, lb, ma):
m3 = mk[:, :, None]
@@ -618,33 +777,68 @@ def _multiband_blend(orig, swap_result, mask_bool, levels, edge_erode_px):
# 这条带正是 mb_levels 要控制的东西。若像旧实现那样用原始硬二值遮罩钳回,
# 过渡带会被整条抹掉(实测 levels 2↔6 边界差恒为 0),mb_levels 形同虚设。
# 故按层数膨胀出一个外缘 keep 区:keep 内允许过渡,keep 外才强制还原原图。
margin = 2 ** n # n=2→4px … n=6→64px,与粗层掩码的自然扩散宽度匹配
if transition_band_px is not None and transition_band_px >= 0:
margin = int(transition_band_px) # 与金字塔层数解耦,用绝对像素
else:
margin = 2 ** n # n=2→4px … n=6→64px,与粗层掩码的自然扩散宽度匹配
margin = max(0, margin)
k = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2 * margin + 1, 2 * margin + 1))
keep = cv2.dilate(mask_bool.astype(np.uint8), k).astype(bool)
out[~keep] = orig[~keep]
return out
def _seamless_clone(orig, swap_result, mask_bool, edge_erode_px):
"""泊松无缝克隆(cv2.seamlessClone NORMAL_CLONE):梯度域调和整体色调。
返回调色后的整帧 uint8 BGR掩码过小<10px时返回原图
seamless 分支与 two_stage 两段式融合的第一段复用
"""
m = mask_bool.astype(np.uint8)
if edge_erode_px > 0:
k = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2 * edge_erode_px + 1,) * 2)
m = cv2.erode(m, k)
if m.sum() < 10:
return orig.copy()
ys, xs = np.where(m > 0)
center = (int((xs.min() + xs.max()) / 2), int((ys.min() + ys.max()) / 2))
return cv2.seamlessClone(swap_result, orig, m * 255, center, cv2.NORMAL_CLONE)
def _composite(orig, swap_result, mask_bool, blend_method, feather_px, edge_erode_px,
color_match=False, mb_levels=5):
"""把 swap_result 按遮罩贴回 orig,返回 (final_bgr, alpha_float or None)。"""
color_match=False, mb_levels=5, color_match_strength=1.0,
mb_feather_px=1, transition_band_px=-1):
"""把 swap_result 按遮罩贴回 orig,返回 (final_bgr, alpha_float or None)。
blend_method:
- multiband : 多频段金字塔融合默认
- seamless : 泊松无缝克隆梯度域调色自带色彩调和故跳过 color_match
- two_stage : seamless 统一整体色调 multiband 贴发丝细节大色差场景
- feather/alpha_gradient : 单层 alpha 过渡
"""
# seamless / two_stage 自带梯度域色彩调和,不叠 Reinhard 颜色迁移
if blend_method == "seamless":
m = mask_bool.astype(np.uint8)
if edge_erode_px > 0:
k = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2 * edge_erode_px + 1,) * 2)
m = cv2.erode(m, k)
if m.sum() < 10:
return orig.copy(), None
ys, xs = np.where(m > 0)
center = (int((xs.min() + xs.max()) / 2), int((ys.min() + ys.max()) / 2))
final = cv2.seamlessClone(swap_result, orig, m * 255, center, cv2.NORMAL_CLONE)
final = _seamless_clone(orig, swap_result, mask_bool, edge_erode_px)
return final, None
# 颜色校正前置(seamless 自带色彩调和,已在上面提前返回;其余分支在此生效)
src = _color_match_to_orig(swap_result, orig, mask_bool) if color_match else swap_result
if blend_method == "two_stage":
# 第一段:seamless 把整体色调拉平(生成图色调对齐到原图)
harmonized = _seamless_clone(orig, swap_result, mask_bool, edge_erode_px)
# 第二段:对调色后的结果再做 multiband 贴发丝细节(不加 color_match,避免重复改色)
final = _multiband_blend(orig, harmonized, mask_bool, mb_levels, edge_erode_px,
feather_px=mb_feather_px,
transition_band_px=transition_band_px)
alpha = (_multiband_alpha(mask_bool, edge_erode_px).astype(np.float32)) / 255.0
return final, alpha
# multiband / feather / alpha_gradient:先做 Reinhard 颜色迁移消除整体色差
src = (_color_match_to_orig(swap_result, orig, mask_bool, color_match_strength)
if color_match else swap_result)
if blend_method == "multiband":
final = _multiband_blend(orig, src, mask_bool, mb_levels, edge_erode_px)
final = _multiband_blend(orig, src, mask_bool, mb_levels, edge_erode_px,
feather_px=mb_feather_px,
transition_band_px=transition_band_px)
# 可视化用:用多频段的二值掩码做一层 alpha 标记(展示实际合成区)
alpha = (_multiband_alpha(mask_bool, edge_erode_px).astype(np.float32)) / 255.0
return final, alpha
@@ -659,26 +853,28 @@ def _composite(orig, swap_result, mask_bool, blend_method, feather_px, edge_erod
# 主入口
# ---------------------------------------------------------------------------
def generate_hairline_grow(image_bgr, hairline_id, is_hr=False, seg_model="segformer",
erode_cm=0.6, swap_mode="ext_mask",
edge_erode_px=3,
denoising_strength=0.6, gen_backend="swaphair",
hairgrow_strength=0.75, mb_levels=5,
hairline_push_cm=1.0, hairline_edge="column", rid=None):
"""接口11 完整管线。返回可直接进 ok() 的 data dict。未检出人脸抛 NoFaceError
def _grow_core(image_bgr, hairline_id, *, is_hr, seg_model, erode_cm, swap_mode,
edge_erode_px, denoising_strength, gen_backend, hairgrow_strength,
mb_levels, hairline_push_cm, hairline_edge, blend_method, color_match,
color_match_strength, mb_feather_px, transition_band_px,
inpainting_fill, mask_blur, mask_dilate_scale, rid, render_viz=True,
hair_mask=None, webui_steps=None):
"""接口11 共享核心:遮罩(pushed)→生成→硬贴回→接缝融合,产出 ④ final
遮罩算法固定为 pushed发际线外推融合算法固定为 multiband多频段金字塔
不再支持其他选项rid: 调用方的 request id用于日志关联 None 时自动生成
不做任何重绘返回中间产物 dict供接口11 构造响应接口12 final+重绘带用
final / swap_result / hard_paste / alpha / mask_bool / mask_viz /
px_per_cm / t_mask / t_swap / t_blend / h / w
未检出人脸抛 NoFaceError
"""
mask_type = "pushed" # 固定:只支持 pushed 遮罩算法
blend_method = "multiband" # 固定:只支持 multiband 融合
if rid is None:
rid = uuid4().hex[:8]
logger.info("[%s] ===== generate_hairline_grow 开始 =====", rid)
logger.info("[%s] 参数(固定 mask=pushed blend=multiband): erode_cm=%s hairline_push_cm=%s "
"hairline_edge=%r mb_levels=%s seg=%s gen_backend=%s swap_mode=%s",
logger.info("[%s] _grow_core 参数(固定 mask=pushed): erode_cm=%s hairline_push_cm=%s "
"hairline_edge=%r mb_levels=%s seg=%s gen_backend=%s swap_mode=%s blend=%s "
"color_match=%s cm_strength=%s mb_feather_px=%s transition_band_px=%s "
"inpainting_fill=%s mask_blur=%s mask_dilate_scale=%s",
rid, erode_cm, hairline_push_cm, hairline_edge, mb_levels,
seg_model, gen_backend, swap_mode)
seg_model, gen_backend, swap_mode, blend_method, color_match,
color_match_strength, mb_feather_px, transition_band_px,
inpainting_fill, mask_blur, mask_dilate_scale)
h, w = image_bgr.shape[:2]
landmarks = detector.detect(image_bgr)
if landmarks is None:
@@ -691,7 +887,8 @@ def generate_hairline_grow(image_bgr, hairline_id, is_hr=False, seg_model="segfo
t0 = time.time()
mask_bool, mask_viz = compute_mask(
image_bgr, landmarks, seg_model, mask_type, erode_cm, px_per_cm,
hairline_push_cm=hairline_push_cm, hairline_edge=hairline_edge, rid=rid)
hairline_push_cm=hairline_push_cm, hairline_edge=hairline_edge, rid=rid,
render_viz=render_viz, hair_mask=hair_mask)
t_mask = time.time() - t0
logger.info("[%s] 步骤1 遮罩完成 耗时=%dms mask_pixels=%d", rid, int(t_mask*1000), int(mask_bool.sum()))
@@ -701,27 +898,80 @@ def generate_hairline_grow(image_bgr, hairline_id, is_hr=False, seg_model="segfo
swap_result = _call_hairgrow(image_bgr, mask_bool, hairgrow_strength)
else:
ext_mask = mask_bool if swap_mode == "ext_mask" else None
swap_result = _call_swap(image_bgr, hairline_id, is_hr, ext_mask, denoising_strength)
swap_result = _call_swap(image_bgr, hairline_id, is_hr, ext_mask, denoising_strength,
inpainting_fill=inpainting_fill, mask_blur=mask_blur,
mask_dilate_scale=mask_dilate_scale, webui_steps=webui_steps)
t_swap = time.time() - t0
# 步骤3:严格按遮罩硬贴回(无融合,用于对比)
hard_paste = image_bgr.copy()
hard_paste[mask_bool] = swap_result[mask_bool]
# 步骤4:接缝融合(固定 multiband
# 步骤4:接缝融合(默认 multiband→ ④ final
t0 = time.time()
final, alpha = _composite(
image_bgr, swap_result, mask_bool, blend_method, 0, edge_erode_px,
color_match=False, mb_levels=mb_levels)
color_match=color_match, mb_levels=mb_levels,
color_match_strength=color_match_strength,
mb_feather_px=mb_feather_px, transition_band_px=transition_band_px)
t_blend = time.time() - t0
return {
"final": final, "swap_result": swap_result, "hard_paste": hard_paste,
"alpha": alpha, "mask_bool": mask_bool, "mask_viz": mask_viz,
"px_per_cm": px_per_cm, "t_mask": t_mask, "t_swap": t_swap, "t_blend": t_blend,
"h": h, "w": w,
}
# ---------------------------------------------------------------------------
# 主入口
# ---------------------------------------------------------------------------
def generate_hairline_grow(image_bgr, hairline_id, is_hr=False, seg_model="segformer",
erode_cm=0.6, swap_mode="ext_mask",
edge_erode_px=3,
denoising_strength=0.6, gen_backend="swaphair",
hairgrow_strength=0.75, mb_levels=5,
hairline_push_cm=1.0, hairline_edge="column",
blend_method="multiband", color_match=True,
color_match_strength=1.0, mb_feather_px=1,
transition_band_px=-1,
inpainting_fill=1, mask_blur=11, mask_dilate_scale=1.0,
rid=None, webui_steps=None):
"""接口11 完整管线(**不含重绘**,重绘见接口12 generate_hairline_redraw)。
返回可直接进 ok() data dict未检出人脸抛 NoFaceError
遮罩算法固定为 pushed发际线外推
融合算法 blend_method 默认 multiband多频段金字塔可选 seamless(泊松)/
two_stage(泊松多频段两段式)/feather(羽化)/alpha_gradient(距离变换)
color_match 默认开启 Reinhard 颜色迁移消除整体色差 multiband/feather 有效
inpainting_fill/mask_blur/mask_dilate_scale透传 change_hair 服务端换发型重绘参数
rid: 调用方的 request id用于日志关联 None 时自动生成
"""
if rid is None:
rid = uuid4().hex[:8]
logger.info("[%s] ===== generate_hairline_grow 开始 =====", rid)
core = _grow_core(
image_bgr, hairline_id, is_hr=is_hr, seg_model=seg_model, erode_cm=erode_cm,
swap_mode=swap_mode, edge_erode_px=edge_erode_px, denoising_strength=denoising_strength,
gen_backend=gen_backend, hairgrow_strength=hairgrow_strength, mb_levels=mb_levels,
hairline_push_cm=hairline_push_cm, hairline_edge=hairline_edge, blend_method=blend_method,
color_match=color_match, color_match_strength=color_match_strength,
mb_feather_px=mb_feather_px, transition_band_px=transition_band_px,
inpainting_fill=inpainting_fill, mask_blur=mask_blur,
mask_dilate_scale=mask_dilate_scale, rid=rid, webui_steps=webui_steps)
mask_viz = core["mask_viz"]
alpha = core["alpha"]
w, h = core["w"], core["h"]
data = {
"hairline_id": hairline_id,
"gen_backend": gen_backend,
"hairgrow_strength": round(float(hairgrow_strength), 3),
"is_hr": is_hr,
"seg_model": seg_model,
"mask_type": mask_type,
"mask_type": "pushed",
"erode_cm": round(float(erode_cm), 2),
"swap_mode": swap_mode,
"blend_method": blend_method,
@@ -730,16 +980,23 @@ def generate_hairline_grow(image_bgr, hairline_id, is_hr=False, seg_model="segfo
"hairline_push_cm": round(float(hairline_push_cm), 2),
"hairline_edge": hairline_edge,
"denoising_strength": round(float(denoising_strength), 3),
"px_per_cm": round(float(px_per_cm), 4),
"color_match": bool(color_match),
"color_match_strength": round(float(color_match_strength), 3),
"mb_feather_px": int(mb_feather_px),
"transition_band_px": int(transition_band_px),
"inpainting_fill": int(inpainting_fill),
"mask_blur": int(mask_blur),
"mask_dilate_scale": round(float(mask_dilate_scale), 3),
"px_per_cm": round(float(core["px_per_cm"]), 4),
"erode_px": mask_viz["erode_px"],
"hair_pixels": mask_viz["hair_pixels"],
"closed_pixels": mask_viz["closed_pixels"],
"mask_pixels": mask_viz["mask_pixels"],
"image_size": {"width": w, "height": h},
"timings_ms": {
"mask": int(t_mask * 1000),
"swap": int(t_swap * 1000),
"blend": int(t_blend * 1000),
"mask": int(core["t_mask"] * 1000),
"swap": int(core["t_swap"] * 1000),
"blend": int(core["t_blend"] * 1000),
},
"steps": {
"input_base64": _jpg_b64(image_bgr),
@@ -755,16 +1012,135 @@ def generate_hairline_grow(image_bgr, hairline_id, is_hr=False, seg_model="segfo
# 最终遮罩
"mask_overlay_base64": mask_viz["mask_overlay_base64"],
"mask_base64": mask_viz["mask_base64"],
"swap_raw_base64": _jpg_b64(swap_result),
"hard_paste_base64": _jpg_b64(hard_paste),
"swap_raw_base64": _jpg_b64(core["swap_result"]),
"hard_paste_base64": _jpg_b64(core["hard_paste"]),
"alpha_base64": _gray_b64(alpha) if alpha is not None else mask_viz["mask_base64"],
"final_base64": _jpg_b64(final),
"final_base64": _jpg_b64(core["final"]),
},
"_rid": rid, # 调试用:返回本次请求的日志关联 id
"_rid": rid,
}
# 记录 steps 各图字段是否非空,供排查前端取图问题
steps_summary = {k: (len(v) if isinstance(v, str) and v else 0)
for k, v in data["steps"].items() if k.endswith("_base64")}
logger.info("[%s] 返回 steps 字段长度: %s", rid, steps_summary)
logger.info("[%s] ===== generate_hairline_grow 完成 =====", rid)
return data
def generate_hairline_redraw(image_bgr, hairline_id, is_hr=False, seg_model="segformer",
erode_cm=0.6, swap_mode="ext_mask",
edge_erode_px=3,
denoising_strength=0.6, gen_backend="swaphair",
hairgrow_strength=0.75, mb_levels=5,
hairline_push_cm=1.0, hairline_edge="column",
blend_method="multiband", color_match=True,
color_match_strength=1.0, mb_feather_px=1,
transition_band_px=-1,
inpainting_fill=1, mask_blur=11, mask_dilate_scale=1.0,
comfyui_prompt=None, beauty_alpha=0.6,
band_lo_mult=0.5, band_hi_mult=1.5, rid=None,
hair_mask=None, webui_steps=None):
"""接口12 发际线带重绘。内部先跑接口11 核心拿到 ④ final,再取 ⑤-① 发际线重绘带
外推内推之间 baseline 截断只留上部作遮罩
**本接口不再做 Flux-2 重绘**只产出 `final`接缝融合基底+ 纯红遮罩
`redraw_band_mask`RGBA遮罩区=(255,0,0,255)其余全透明重绘交给后端
ComfyUI 重绘接口/api/v1/redraw完成旧的 `redraw_full` / `redraw_band`
字段保留为空仅作结构兼容
返回可直接进 ok() data dict未检出人脸抛 NoFaceError
comfyui_prompt保留入参但本接口不再使用重绘提示词由外部服务自行决定
beauty_alpha保留入参但本接口不再使用美颜由外部服务控制
band_lo_mult / band_hi_mult重绘带外推倍率相对 hairline_push_cm带位于
lo×push ~ hi×push 之间内轮廓=0×原外推线=1.0×默认 0.5 / 1.5
其余参数含义与接口11 相同用于内部生成 final 与重绘带
"""
if rid is None:
rid = uuid4().hex[:8]
logger.info("[%s] ===== generate_hairline_redraw 开始 =====", rid)
core = _grow_core(
image_bgr, hairline_id, is_hr=is_hr, seg_model=seg_model, erode_cm=erode_cm,
swap_mode=swap_mode, edge_erode_px=edge_erode_px, denoising_strength=denoising_strength,
gen_backend=gen_backend, hairgrow_strength=hairgrow_strength, mb_levels=mb_levels,
hairline_push_cm=hairline_push_cm, hairline_edge=hairline_edge, blend_method=blend_method,
color_match=color_match, color_match_strength=color_match_strength,
mb_feather_px=mb_feather_px, transition_band_px=transition_band_px,
inpainting_fill=inpainting_fill, mask_blur=mask_blur,
mask_dilate_scale=mask_dilate_scale, rid=rid, render_viz=False,
hair_mask=hair_mask, webui_steps=webui_steps)
final = core["final"]
mask_viz = core["mask_viz"]
w, h = core["w"], core["h"]
px_per_cm = core["px_per_cm"]
# ① 算重绘带(⑤-①):发际线(内轮廓)↔外推发际线成带,经 baseline 截断只留上部
t0 = time.time()
inner_pts = mask_viz.get("_inner_pts")
outer_pts = mask_viz.get("_outer_pts")
upper_mask = mask_viz.get("_upper_mask")
push_px = int(round(max(0.0, hairline_push_cm) * px_per_cm))
redraw_band_overlay_b64 = ""
redraw_band_mask_b64 = "" # 纯红 alpha PNG(遮罩区=(255,0,0,255),其余全透明)
redraw_info = {"enabled": False}
band_mask = None
try:
band_mask = _redraw_band_mask(inner_pts, outer_pts, h, w, rid=rid, upper=upper_mask,
lo_mult=band_lo_mult, hi_mult=band_hi_mult)
if band_mask.sum() < 30:
raise RuntimeError("重绘带像素过少,可能内轮廓/外推线缺失")
logger.info("[%s] 重绘带 push_px=%d lo_mult=%s hi_mult=%s band_pixels=%d",
rid, push_px, band_lo_mult, band_hi_mult, int(band_mask.sum()))
redraw_band_overlay_b64 = _jpg_b64(_overlay(final, band_mask, (255, 0, 255)))
# 纯红遮罩 PNG(供外部重绘服务按 alpha 识别重绘区)
redraw_band_mask_b64 = _red_mask_b64(band_mask, h, w)
redraw_info = {"enabled": True, "band_pixels": int(band_mask.sum()), "push_px": push_px,
"band_lo_mult": float(band_lo_mult), "band_hi_mult": float(band_hi_mult)}
except Exception as ex: # noqa: BLE001
logger.exception("[%s] 重绘带计算失败,整个重绘跳过", rid)
redraw_info = {"enabled": False, "error": f"band: {ex}"}
# ② Flux-2 重绘已下线:本接口现在只产出 final(接缝融合基底)+ 纯红重绘带遮罩,
# 重绘交给后端 ComfyUI 重绘接口(/api/v1/redraw)完成。
# 下面保留 redraw_full_b64 / redraw_band_b64 为空,保持返回结构兼容(旧字段)。
redraw_full_b64 = ""
redraw_band_b64 = ""
t_redraw = time.time() - t0
data = {
"hairline_id": hairline_id,
"blend_method": blend_method,
"hairline_push_cm": round(float(hairline_push_cm), 2),
"comfyui_prompt": comfyui_prompt or "填充遮罩区域的头发",
"beauty_alpha": beauty_alpha,
"px_per_cm": round(float(px_per_cm), 4),
"mask_pixels": mask_viz["mask_pixels"],
"image_size": {"width": w, "height": h},
"timings_ms": {
"mask": int(core["t_mask"] * 1000),
"swap": int(core["t_swap"] * 1000),
"blend": int(core["t_blend"] * 1000),
"redraw": int(t_redraw * 1000),
},
"steps": {
"input_base64": _jpg_b64(image_bgr),
# 接口11 的 ④ final —— 作为本接口的重绘输入基底
"final_base64": _jpg_b64(final),
# ⑤-① 发际线重绘带(紫,已按 baseline 截断只留上部)
"redraw_band_overlay_base64": redraw_band_overlay_b64,
# ⑤-② 发际线重绘带遮罩(纯红 alpha PNG,遮罩区=(255,0,0,255)
"redraw_band_mask_base64": redraw_band_mask_b64,
# A:ComfyUI 整帧重绘+美颜(已下线,保留空字段兼容旧前端)
"redraw_full_base64": redraw_full_b64,
# B:加发只在发际线带、美颜保留全脸(已下线,保留空字段兼容旧前端)
"redraw_band_base64": redraw_band_b64,
# 兼容旧字段:指向 A(整帧版)
"redraw_c_base64": redraw_full_b64,
},
"redraw": redraw_info,
"_rid": rid,
}
steps_summary = {k: (len(v) if isinstance(v, str) and v else 0)
for k, v in data["steps"].items() if k.endswith("_base64")}
logger.info("[%s] 返回 steps 字段长度: %s", rid, steps_summary)
logger.info("[%s] ===== generate_hairline_redraw 完成 =====", rid)
return data
+5 -3
View File
@@ -22,9 +22,11 @@ import numpy as np
from face_analysis.detector import detector
from face_analysis.calibration import estimate_scale_factor, normalized_to_pixel
# 底部分割线关键点(图像上从左到右:左端 162 → 中心 151 → 右端 389
# 162/389 为左右最外侧端点(向图片左右边缘水平延长);中间含 71/301 等点构成弧线
BASELINE_IDX = [162, 71, 68, 104, 69, 108, 151, 337, 299, 333, 298, 301, 389]
# 底部分割线关键点(图像上从左到右,眉骨弧线 → 中心 151 → 右侧对称
# 左端 104 → 中心 151 → 右端 333;首末点向图片左右边缘水平延长
# BASELINE_IDX = [104, 69, 108, 151, 337, 299, 333]
# BASELINE_IDX = [34, 139, 71, 68, 104, 69, 108, 151, 337, 299, 333, 298, 301, 368, 264]
BASELINE_IDX = [71, 68, 104, 69, 108, 151, 337, 299, 333, 298, 301]
CENTER_IDX = 151 # 内缩方向的目标点(额头中心)
ERODE_CM = 1.2 # 外缘内缩距离(厘米,默认;可由入参覆盖)
SEGFORMER_HAIR = 13 # jonathandinu/face-parsing 中 hair 类索引
+113 -47
View File
@@ -12,9 +12,9 @@ from face_analysis.calibration import (
estimate_scale_factor, normalized_to_pixel, pixel_distance, _lm_list,
)
from face_analysis.face_mesh_landmarks import (
GLABELLA_9, GLABELLA_151, NOSE_BOTTOM, CHIN_TIP,
GLABELLA_9, NOSE_BOTTOM, CHIN_TIP,
LEFT_EYE_OUTER, LEFT_EYE_INNER, RIGHT_EYE_INNER, RIGHT_EYE_OUTER,
LEFT_CHEEK, RIGHT_CHEEK,
LEFT_CHEEK, RIGHT_CHEEK, LEFT_POSITION, RIGHT_POSITION,
)
from face_analysis.hair_segmenter import locate_hairline_by_segmentation
@@ -24,10 +24,8 @@ _TOP_RATIO = 0.22 / 0.28 # 顶庭 ÷ 中庭(≈ 0.786)
def _brow_center(lm, w, h):
"""眉心 = 索引 9 / 151 中点"""
g9 = normalized_to_pixel(lm[GLABELLA_9], w, h)
g151 = normalized_to_pixel(lm[GLABELLA_151], w, h)
return (g9[0] + g151[0]) / 2, (g9[1] + g151[1]) / 2
"""眉心 = 索引 9(眉间上点)"""
return normalized_to_pixel(lm[GLABELLA_9], w, h)
def estimate_vertical_landmarks(landmarks, image_width, image_height):
@@ -144,22 +142,47 @@ def measure_seven_eyes(landmarks, image_width, image_height):
}
def pt_or_none(vertical, name):
"""vertical dict 的点 → {"x","y"},值为 None 时返回 None。"""
v = vertical.get(name)
if v is None:
return None
return {"x": int(round(v[0])), "y": int(round(v[1]))}
class MeasureResult:
"""测量结果,提供 to_response() 输出与接口文档同构的 data 字段。"""
def __init__(self, vertical, eyes, px_per_cm, hairline_source, head_pose):
# 发际线弃用阈值:发际线离头顶(顶庭)< 此值时判定分割不可靠,弃用发际线。
# hairline 与 hair_top 几乎重合(如稀疏头发中轴漏检只剩一小撮),说明发际线
# 定位无意义 → 顶/上庭置 null、标注图不画头顶/发际线。
HAIRLINE_DISCARD_TOP_CM = 0.7
def __init__(self, vertical, eyes, px_per_cm, hairline_source, head_pose,
landmarks=None, image_width=None, image_height=None):
self.vertical = vertical
self.eyes = eyes
self.px_per_cm = px_per_cm
self.hairline_source = hairline_source
self.head_pose = head_pose # (yaw, pitch, roll) 或 None
# 原始 mediapipe 点集 + 图像尺寸,供 to_response 输出 21/251 号定位点
self.landmarks = landmarks
self.w = image_width
self.h = image_height
# 各庭厘米
self.top_cm = vertical["top_court_px"] / px_per_cm
self.upper_cm = vertical["upper_court_px"] / px_per_cm
self.middle_cm = vertical["middle_court_px"] / px_per_cm
self.lower_cm = vertical["lower_court_px"] / px_per_cm
self.face_total_cm = self.top_cm + self.upper_cm + self.middle_cm + self.lower_cm
# 发际线弃用判定:顶庭(头顶→发际线)过小视为发际线贴近头顶、不可靠。
# 弃用时 hairline_source 改为 "discarded"face_total 只算中庭+下庭。
self.hairline_discarded = self.top_cm < self.HAIRLINE_DISCARD_TOP_CM
if self.hairline_discarded:
self.hairline_source = "discarded"
self.face_total_cm = self.middle_cm + self.lower_cm
else:
self.face_total_cm = self.top_cm + self.upper_cm + self.middle_cm + self.lower_cm
# 七眼厘米
self.eye_width_cm = eyes["eye_width_px"] / px_per_cm
@@ -167,46 +190,88 @@ class MeasureResult:
self.inter_eye_cm = eyes["inter_eye_distance_px"] / px_per_cm
def to_response(self):
total_px = (self.vertical["top_court_px"] + self.vertical["upper_court_px"]
+ self.vertical["middle_court_px"] + self.vertical["lower_court_px"])
fw_px = self.eyes["face_width_px"]
def pt(name):
x, y = self.vertical[name]
return {"x": int(round(x)), "y": int(round(y))}
data = {
"face_total_height_cm": round(self.face_total_cm, 2),
"four_courts": {
"top_court_cm": round(self.top_cm, 2),
"upper_court_cm": round(self.upper_cm, 2),
"middle_court_cm": round(self.middle_cm, 2),
"lower_court_cm": round(self.lower_cm, 2),
"ratios": {
"top_court": round(self.vertical["top_court_px"] / total_px, 3),
"upper_court": round(self.vertical["upper_court_px"] / total_px, 3),
"middle_court": round(self.vertical["middle_court_px"] / total_px, 3),
"lower_court": round(self.vertical["lower_court_px"] / total_px, 3),
# 发际线弃用:顶/上庭相关字段置 null(保留键),ratio 分母只算中下庭;
# landmarks.hair_top/hairline 置 null。否则按四庭正常输出。
if self.hairline_discarded:
base_px = (self.vertical["middle_court_px"] + self.vertical["lower_court_px"])
data = {
"face_total_height_cm": round(self.face_total_cm, 2),
"four_courts": {
"top_court_cm": None,
"upper_court_cm": None,
"middle_court_cm": round(self.middle_cm, 2),
"lower_court_cm": round(self.lower_cm, 2),
"ratios": {
"top_court": None,
"upper_court": None,
"middle_court": round(self.vertical["middle_court_px"] / base_px, 3),
"lower_court": round(self.vertical["lower_court_px"] / base_px, 3),
},
},
},
"seven_eyes": {
"eye_width_cm": round(self.eye_width_cm, 2),
"face_width_cm": round(self.face_width_cm, 2),
"inter_eye_distance_cm": round(self.inter_eye_cm, 2),
"ratios": {
"eye_width": round(self.eyes["eye_width_px"] / fw_px, 3),
"inter_eye_distance": round(self.eyes["inter_eye_distance_px"] / fw_px, 3),
"seven_eyes": {
"eye_width_cm": round(self.eye_width_cm, 2),
"face_width_cm": round(self.face_width_cm, 2),
"inter_eye_distance_cm": round(self.inter_eye_cm, 2),
"ratios": {
"eye_width": round(self.eyes["eye_width_px"] / self.eyes["face_width_px"], 3),
"inter_eye_distance": round(self.eyes["inter_eye_distance_px"] / self.eyes["face_width_px"], 3),
},
},
},
"landmarks": {
"hair_top": pt("hair_top"),
"hairline": pt("hairline"),
"brow_center": pt("brow_center"),
"nose_bottom": pt("nose_bottom"),
"chin_tip": pt("chin_tip"),
},
"hairline_source": self.hairline_source,
}
"landmarks": {
"hair_top": None,
"hairline": None,
"brow_center": pt_or_none(self.vertical, "brow_center"),
"nose_bottom": pt_or_none(self.vertical, "nose_bottom"),
"chin_tip": pt_or_none(self.vertical, "chin_tip"),
},
"hairline_source": self.hairline_source,
}
else:
total_px = (self.vertical["top_court_px"] + self.vertical["upper_court_px"]
+ self.vertical["middle_court_px"] + self.vertical["lower_court_px"])
data = {
"face_total_height_cm": round(self.face_total_cm, 2),
"four_courts": {
"top_court_cm": round(self.top_cm, 2),
"upper_court_cm": round(self.upper_cm, 2),
"middle_court_cm": round(self.middle_cm, 2),
"lower_court_cm": round(self.lower_cm, 2),
"ratios": {
"top_court": round(self.vertical["top_court_px"] / total_px, 3),
"upper_court": round(self.vertical["upper_court_px"] / total_px, 3),
"middle_court": round(self.vertical["middle_court_px"] / total_px, 3),
"lower_court": round(self.vertical["lower_court_px"] / total_px, 3),
},
},
"seven_eyes": {
"eye_width_cm": round(self.eye_width_cm, 2),
"face_width_cm": round(self.face_width_cm, 2),
"inter_eye_distance_cm": round(self.inter_eye_cm, 2),
"ratios": {
"eye_width": round(self.eyes["eye_width_px"] / self.eyes["face_width_px"], 3),
"inter_eye_distance": round(self.eyes["inter_eye_distance_px"] / self.eyes["face_width_px"], 3),
},
},
"landmarks": {
"hair_top": pt_or_none(self.vertical, "hair_top"),
"hairline": pt_or_none(self.vertical, "hairline"),
"brow_center": pt_or_none(self.vertical, "brow_center"),
"nose_bottom": pt_or_none(self.vertical, "nose_bottom"),
"chin_tip": pt_or_none(self.vertical, "chin_tip"),
},
"hairline_source": self.hairline_source,
}
# left/right_positionmediapipe 21/251 号定位点(原图像素,与 landmarks 同坐标系)。
# landmarks 缺省(如测试直构 MeasureResult)时不输出,保持向后兼容。
if self.landmarks is not None and self.w and self.h:
lm = _lm_list(self.landmarks)
def _pt_lm(idx):
px, py = normalized_to_pixel(lm[idx], self.w, self.h)
return {"x": int(round(px)), "y": int(round(py))}
data["left_position"] = _pt_lm(LEFT_POSITION)
data["right_position"] = _pt_lm(RIGHT_POSITION)
if self.head_pose is not None:
yaw, pitch, roll = self.head_pose
data["head_pose"] = {
@@ -220,7 +285,8 @@ def measure_face(landmarks, hair_mask, image_width, image_height, head_pose=None
vertical, source = decide_vertical(landmarks, image_width, image_height, hair_mask)
eyes = measure_seven_eyes(landmarks, image_width, image_height)
px_per_cm = estimate_scale_factor(landmarks, image_width, image_height)
return MeasureResult(vertical, eyes, px_per_cm, source, head_pose)
return MeasureResult(vertical, eyes, px_per_cm, source, head_pose,
landmarks, image_width, image_height)
if __name__ == "__main__":
+10 -1
View File
@@ -50,12 +50,21 @@ def estimate_head_pose(landmarks, image_width, image_height):
[0, 0, 1]], dtype=np.float64)
dist = np.zeros((4, 1)) # 假设无畸变
success, rvec, _tvec = cv2.solvePnP(
success, rvec, tvec = cv2.solvePnP(
_MODEL_POINTS, image_points, cam_matrix, dist,
flags=cv2.SOLVEPNP_ITERATIVE,
)
if not success:
return None
# ITERATIVE 偶发收敛到相机后方的翻转解(tz<0),此时 roll 落在 ±180° 附近,
# 会把真正的正面照误判为 1003。改用 SQPNP 重解正深度解。
if float(tvec[2, 0]) < 0:
ok2, rvec2, tvec2 = cv2.solvePnP(
_MODEL_POINTS, image_points, cam_matrix, dist,
flags=cv2.SOLVEPNP_SQPNP,
)
if ok2 and float(tvec2[2, 0]) > 0:
rvec = rvec2
rot, _ = cv2.Rodrigues(rvec)
# 在「相机坐标系」(x右 y下 z内) 下抽取 Tait-Bryan 欧拉角,物理含义对齐:
# yaw = 绕 Y(竖轴)转 → 左右扭头
+8 -9
View File
@@ -1,16 +1,15 @@
[Unit]
Description=Hair Worker (GPU) - 四庭七眼测量 接口1
After=network.target
Description=hair GPU worker FastAPI (0.0.0.0:8187)
After=network-online.target comfyui.service change_hair-hair.service
Wants=comfyui.service change_hair-hair.service
[Service]
Type=simple
User=xsl
WorkingDirectory=/home/xsl/hair
# 鉴权密码:优先 worker_config.json;也可在此用环境变量覆盖
# Environment=WORKER_ACCEPT_PASSWORDS=your-strong-secret
ExecStart=/home/xsl/hair/venv/bin/uvicorn app:app --host 0.0.0.0 --port 8187
Restart=always
RestartSec=3
User=ubuntu
WorkingDirectory=/home/ubuntu/hair
ExecStart=/home/ubuntu/hair/venv/bin/uvicorn app:app --host 0.0.0.0 --port 8187
Restart=on-failure
RestartSec=5
[Install]
WantedBy=multi-user.target
+450
View File
@@ -0,0 +1,450 @@
{
"1": {
"inputs": {
"scheduler": "simple",
"steps": 6,
"denoise": 1,
"model": [
"2",
0
]
},
"class_type": "BasicScheduler",
"_meta": {
"title": "基本调度器"
}
},
"2": {
"inputs": {
"max_shift": 1.15,
"base_shift": 0.5,
"width": [
"14",
0
],
"height": [
"14",
1
],
"model": [
"16",
0
]
},
"class_type": "ModelSamplingFlux",
"_meta": {
"title": "采样算法(Flux"
}
},
"3": {
"inputs": {
"vae_name": "flux2-vae.safetensors"
},
"class_type": "VAELoader",
"_meta": {
"title": "加载VAE"
}
},
"5": {
"inputs": {
"conditioning": [
"19",
0
],
"latent": [
"13",
0
]
},
"class_type": "ReferenceLatent",
"_meta": {
"title": "参考Latent"
}
},
"6": {
"inputs": {
"noise_seed": 808990860769642
},
"class_type": "RandomNoise",
"_meta": {
"title": "随机噪波"
}
},
"7": {
"inputs": {
"width": [
"14",
0
],
"height": [
"14",
1
],
"batch_size": 1
},
"class_type": "EmptySD3LatentImage",
"_meta": {
"title": "空Latent图像(SD3"
}
},
"8": {
"inputs": {
"sampler_name": "euler"
},
"class_type": "KSamplerSelect",
"_meta": {
"title": "K采样器选择"
}
},
"9": {
"inputs": {
"noise": [
"6",
0
],
"guider": [
"20",
0
],
"sampler": [
"8",
0
],
"sigmas": [
"1",
0
],
"latent_image": [
"7",
0
]
},
"class_type": "SamplerCustomAdvanced",
"_meta": {
"title": "自定义采样器(高级)"
}
},
"10": {
"inputs": {
"samples": [
"9",
0
],
"vae": [
"3",
0
]
},
"class_type": "VAEDecode",
"_meta": {
"title": "VAE解码"
}
},
"13": {
"inputs": {
"pixels": [
"44",
0
],
"vae": [
"3",
0
]
},
"class_type": "VAEEncode",
"_meta": {
"title": "VAE编码"
}
},
"14": {
"inputs": {
"image": [
"44",
0
]
},
"class_type": "GetImageSize+",
"_meta": {
"title": "🔧 Get Image Size"
}
},
"16": {
"inputs": {
"unet_name": "flux-2-klein-9b-Q4_K_M.gguf",
"weight_dtype": "fp8_e4m3fn"
},
"class_type": "UnetLoaderGGUF",
"_meta": {
"title": "UNet加载器"
}
},
"17": {
"inputs": {
"filename_prefix": "ComfyUI",
"images": [
"62",
0
]
},
"class_type": "SaveImage",
"_meta": {
"title": "保存图像"
}
},
"19": {
"inputs": {
"guidance": 1,
"conditioning": [
"22",
0
]
},
"class_type": "FluxGuidance",
"_meta": {
"title": "Flux引导"
}
},
"20": {
"inputs": {
"model": [
"2",
0
],
"conditioning": [
"5",
0
]
},
"class_type": "BasicGuider",
"_meta": {
"title": "基本引导器"
}
},
"22": {
"inputs": {
"text": [
"60",
0
],
"clip": [
"61",
0
]
},
"class_type": "CLIPTextEncode",
"_meta": {
"title": "CLIP文本编码"
}
},
"26": {
"inputs": {
"image": "clipspace/clipspace-painted-masked-1784045785080.png [input]"
},
"class_type": "LoadImage",
"_meta": {
"title": "加载图像"
}
},
"31": {
"inputs": {
"image": [
"26",
0
]
},
"class_type": "easy imageSize",
"_meta": {
"title": "图像尺寸"
}
},
"32": {
"inputs": {
"aspect_ratio": "custom",
"proportional_width": [
"31",
0
],
"proportional_height": [
"31",
1
],
"fit": "letterbox",
"method": "lanczos",
"round_to_multiple": "8",
"scale_to_side": "None",
"scale_to_length": 1024,
"background_color": "#000000",
"image": [
"26",
0
],
"mask": [
"37",
0
]
},
"class_type": "LayerUtility: ImageScaleByAspectRatio V2",
"_meta": {
"title": "LayerUtility: ImageScaleByAspectRatio V2"
}
},
"33": {
"inputs": {
"masks": [
"26",
1
]
},
"class_type": "Mask Fill Holes",
"_meta": {
"title": "遮罩填充漏洞"
}
},
"36": {
"inputs": {
"masks": [
"33",
0
]
},
"class_type": "Convert Masks to Images",
"_meta": {
"title": "遮罩到图像"
}
},
"37": {
"inputs": {
"method": "intensity",
"image": [
"39",
0
]
},
"class_type": "Image To Mask",
"_meta": {
"title": "图像到遮罩"
}
},
"39": {
"inputs": {
"upscale_method": "nearest-exact",
"width": [
"31",
0
],
"height": [
"31",
1
],
"crop": "disabled",
"image": [
"36",
0
]
},
"class_type": "ImageScale",
"_meta": {
"title": "缩放图像"
}
},
"44": {
"inputs": {
"mask_opacity": 1,
"mask_color": "FFFF00",
"pass_through": true,
"image": [
"32",
0
],
"mask": [
"32",
1
]
},
"class_type": "ImageAndMaskPreview",
"_meta": {
"title": "图像与遮罩预览"
}
},
"45": {
"inputs": {
"images": [
"44",
0
]
},
"class_type": "PreviewImage",
"_meta": {
"title": "预览图像"
}
},
"53": {
"inputs": {
"rgthree_comparer": {
"images": [
{
"name": "A",
"selected": true,
"url": "/api/view?filename=rgthree.compare._temp_kzrpg_00019_.png&type=temp&subfolder=&rand=0.8964945384546902"
},
{
"name": "B",
"selected": true,
"url": "/api/view?filename=rgthree.compare._temp_kzrpg_00020_.png&type=temp&subfolder=&rand=0.6762414189274947"
}
]
},
"image_a": [
"62",
0
],
"image_b": [
"26",
0
]
},
"class_type": "Image Comparer (rgthree)",
"_meta": {
"title": "图像对比"
}
},
"60": {
"inputs": {
"text": "填充遮罩区域的头发"
},
"class_type": "JjkText",
"_meta": {
"title": "Text"
}
},
"61": {
"inputs": {
"clip_name": "qwen_3_8b_fp8mixed.safetensors",
"type": "flux2",
"device": "default"
},
"class_type": "CLIPLoader",
"_meta": {
"title": "加载CLIP"
}
},
"62": {
"inputs": {
"method": "mkl",
"strength": 1,
"multithread": true,
"image_ref": [
"26",
0
],
"image_target": [
"10",
0
]
},
"class_type": "ColorMatch",
"_meta": {
"title": "Color Match"
}
}
}
+84 -6
View File
@@ -1,8 +1,9 @@
"""ComfyUI 客户端:用 add_hair.json / add_hair2.json 工作流跑生发图(Flux-2 inpaint)。
worker 不跑 Flux只把划线图 + 遮罩 RGBA 上传到本机 ComfyUI(默认 8188)
worker 不跑 Flux只把划线图 + 遮罩 RGBA 上传到远端 ComfyUI
默认 http://10.60.74.221:8188可用环境变量 COMFYUI_URL 覆盖
替换工作流节点 26 的输入图随机 seed提交 /prompt轮询 /history取回 /view 输出
ComfyUI 开启了 HTTP Basic Authuser `admin` + 密码所有请求都带凭据
ComfyUI 开启了 HTTP Basic Authuser `admin` + 密码所有请求都带凭据
支持多工作流run() 可通过 workflow_path 指定不同工作流 JSON自动检测 SaveImage 输出节点
"""
@@ -10,6 +11,7 @@ from __future__ import annotations
import copy
import json
import logging
import os
import random
import time
@@ -28,6 +30,29 @@ _REPO = os.path.dirname(os.path.dirname(__file__))
_INPUT_NODE = "26" # LoadImage:外部输入图(含 alpha 遮罩)
_SEED_NODE = "6" # RandomNoise
_PROMPT_NODE = "60" # JjkText:提示词
_UNET_NODE = "16" # UNETLoader / UnetLoaderGGUFFlux 模型加载
_CLIP_NODE = "61" # CLIPLoaderqwen 文本编码器
_VAE_NODE = "3" # VAELoader
# Flux 模型 → 配套文本编码器映射。切换 unet 时自动同步编码器,避免维度不匹配。
def _clip_for_unet(unet_name: str) -> str | None:
"""根据 unet 文件名推断配套的文本编码器文件名;无法推断返回 None。"""
low = unet_name.lower()
if "9b" in low: # Flux.2 9B 系列
return "qwen_3_8b_fp8mixed.safetensors"
if "z-image" in low: # Z-Image-Turbo 用 4B 编码器
return "qwen_3_4b.safetensors"
if "4b" in low: # Flux.2 4B
return "qwen_3_4b.safetensors"
return None
# Flux 模型 → 配套 VAE 映射。Z-Image 用 ae.safetensorsFlux.2 系列用 flux2-vae。
def _vae_for_unet(unet_name: str) -> str | None:
"""根据 unet 文件名推断配套 VAE 文件名;无法推断返回 None(保持工作流原值)。"""
low = unet_name.lower()
if "z-image" in low:
return "ae.safetensors"
return None # Flux.2 系列 vae 在工作流里已正确配置,不覆盖
_wf_cache: dict[str, dict] = {} # path → workflow JSON
_wf_output_node: dict[str, str] = {} # path → SaveImage 节点 ID
@@ -84,11 +109,18 @@ def _get_output_node(workflow_path: str | None = None) -> str:
def run(rgba_png_bytes: bytes, timeout: float = COMFY_TIMEOUT, prompt: str = None,
workflow_path: str | None = None) -> bytes:
workflow_path: str | None = None, front: bool = False,
unet_name: str | None = None) -> bytes:
"""提交一次生发任务,返回输出 PNG 字节。失败抛异常。
prompt None 时替换工作流节点60(JjkText)的文本None 时用工作流内置默认提示词
workflow_path工作流 JSON 路径None 则用默认 add_hair.json
frontTrue 时任务插到 ComfyUI 队列最前server "front" 字段队列号取负
接口2 对时延敏感用 True避免排在接口3/5 的批量任务后面其余接口保持 False
unet_name None 时改写工作流里的模型加载节点节点16动态切换 Flux 模型
.safetensors 保持 UNETLoader 节点类型不变只替换 unet_name
.gguf 自动把节点类型改成 UnetLoaderGGUF需装 ComfyUI-GGUF 插件
None 时用工作流内置默认模型
"""
path = workflow_path or _WORKFLOW_DEFAULT
output_node = _get_output_node(path)
@@ -103,14 +135,60 @@ def run(rgba_png_bytes: bytes, timeout: float = COMFY_TIMEOUT, prompt: str = Non
name = (up.get("subfolder") + "/" if up.get("subfolder") else "") + up["name"]
# 2. 改工作流:节点26 输入图 + 随机 seed
try:
import io as _io
from PIL import Image as _Img
_sz = _Img.open(_io.BytesIO(rgba_png_bytes)).size
logging.getLogger("hair.worker").info(
"ComfyUI 输入尺寸 %dx%d workflow=%s", _sz[0], _sz[1], os.path.basename(path))
except Exception: # noqa: BLE001
pass
wf = copy.deepcopy(_load_workflow(path))
wf[_INPUT_NODE]["inputs"]["image"] = name
wf[_SEED_NODE]["inputs"]["noise_seed"] = random.randint(0, 2**63 - 1)
if prompt is not None:
wf[_PROMPT_NODE]["inputs"]["text"] = prompt
if unet_name is not None:
node = wf.get(_UNET_NODE)
if node is not None:
# .gguf 需切换到 ComfyUI-GGUF 插件的 UnetLoaderGGUF 节点;
# .safetensors/.ckpt 保持原 UNETLoader 节点类型不变
if unet_name.lower().endswith(".gguf"):
node["class_type"] = "UnetLoaderGGUF"
else:
node["class_type"] = "UNETLoader"
node["inputs"]["unet_name"] = unet_name
# 同步切换配套文本编码器(4b→qwen_3_4b, 9b→qwen_3_8b),避免维度不匹配
clip_node = wf.get(_CLIP_NODE)
clip_name = _clip_for_unet(unet_name)
if clip_node is not None and clip_name is not None:
clip_node["inputs"]["clip_name"] = clip_name
# 同步切换 VAEZ-Image 用 ae.safetensorsFlux.2 保持 flux2-vae
vae_node = wf.get(_VAE_NODE)
vae_name = _vae_for_unet(unet_name)
if vae_node is not None and vae_name is not None:
vae_node["inputs"]["vae_name"] = vae_name
# 3. 提交
r = cli.post("/prompt", json={"prompt": wf, "client_id": client_id})
# 诊断:落盘实际提交的工作流 + 输入图,便于和手动 ComfyUI 跑的对比
try:
import os as _os
_diag = _os.path.join(_os.path.dirname(_os.path.dirname(_os.path.abspath(__file__))),
"log", "comfyui_last_submit")
_os.makedirs(_diag, exist_ok=True)
with open(_os.path.join(_diag, "workflow.json"), "w", encoding="utf-8") as _f:
json.dump(wf, _f, ensure_ascii=False, indent=2)
with open(_os.path.join(_diag, "input.png"), "wb") as _f:
_f.write(rgba_png_bytes)
with open(_os.path.join(_diag, "prompt.txt"), "w", encoding="utf-8") as _f:
_f.write(prompt if prompt is not None else "(None=用工作流内置默认)")
except Exception: # noqa: BLE001
pass
# 3. 提交(front=True 时插队到队列最前)
payload = {"prompt": wf, "client_id": client_id}
if front:
payload["front"] = True
r = cli.post("/prompt", json=payload)
r.raise_for_status()
prompt_id = r.json()["prompt_id"]
@@ -129,7 +207,7 @@ def run(rgba_png_bytes: bytes, timeout: float = COMFY_TIMEOUT, prompt: str = Non
outputs = entry.get("outputs")
if outputs and output_node in outputs:
break
time.sleep(1.0)
time.sleep(0.05)
if not outputs or output_node not in outputs:
raise TimeoutError(f"ComfyUI 出图超时({timeout}s) prompt_id={prompt_id}")
+47
View File
@@ -186,6 +186,53 @@ def smooth_hairline_corner_aware(
return out
def clamp_hairline_to_silhouette(
hairline_norm: np.ndarray,
parse_map: np.ndarray,
margin_px: float = 2.0,
) -> np.ndarray:
"""把发际线点的 y 钳制在 (skinhair) silhouette 上沿之下(不含 margin 以上)。
根因 issue男性 ellipse 发际线贴到头部外面`sample_hairline` 对射线
未命中 hair 像素的锚点会 fallback 锚点 + 固定 0.18 归一化偏移与头部实际
大小/位置无关 短发/剃光头场景下这个偏移量常常把点顶到头部轮廓外面的背景里
在有效/失效锚点交界处形成尖角被贴图上的不透明像素蒙到就会露出戳出头部的线条
本函数在几何检测之后追加一步安全网对每个点按其 x 所在列 silhouette
SegFormer skinhair 近似头部实际轮廓上沿 y若点比这个上沿还高y
直接钳制到 上沿 + margin_px 保证曲线永远不会跑到头部轮廓外面的背景
"""
h, w = parse_map.shape
cols_with_head, top_y = _head_top_y_per_column(parse_map, use_full_hair=True)
if cols_with_head.size == 0:
return hairline_norm
out = hairline_norm.copy()
for i in range(out.shape[0]):
x_px = float(out[i, 0]) * w
idx = int(np.searchsorted(cols_with_head, x_px))
idx = min(max(idx, 0), cols_with_head.size - 1)
sil_y = float(top_y[idx]) + margin_px
y_px = float(out[i, 1]) * h
if y_px < sil_y:
out[i, 1] = sil_y / h
return out
def sample_hairline_clamped(
landmarks_norm: np.ndarray,
parse_map: np.ndarray,
fallback_extrapolation: float = 0.18,
) -> tuple[np.ndarray, np.ndarray]:
"""策略 A(baseline + 头部轮廓钳制):与默认 `sample_hairline` 完全一致的检测,
额外用 `clamp_hairline_to_silhouette` 兜底 检测失效 fallback 出的点不再可能
跑到头部外面的背景而是贴着头部实际轮廓顶部改动小风险低只在检测失效/
fallback 越界时才生效正常长发照片的结果与 baseline 完全一致
"""
hairline, valid = sample_hairline(landmarks_norm, parse_map, fallback_extrapolation)
hairline = clamp_hairline_to_silhouette(hairline, parse_map)
return hairline, valid
# ---------------------------------------------------------------------------
# Alternative hairline sampling strategies.
#
+80
View File
@@ -0,0 +1,80 @@
"""直接调 ComfyUI 重绘 — 替代 local_test HTTP 服务。
local_test/app.py 的核心逻辑遮罩处理 + ComfyUI 调用提取为 Python 函数
不再需要独立 Flask 服务使用 0716add-hair-api.json 工作流steps=4
"""
from __future__ import annotations
import io
import logging
import os
import numpy as np
from PIL import Image, ImageFilter
from . import comfyui
logger = logging.getLogger("hair.worker")
_DEFAULT_PROMPT = "填充遮罩区域的头发"
_REPO = os.path.dirname(os.path.dirname(__file__))
_REPAINT_WORKFLOW = os.path.join(_REPO, "0716add-hair-api.json")
def _process_mask_to_rgba(image_bytes: bytes, mask_bytes: bytes) -> bytes:
"""将分开的 image + mask 处理为 ComfyUI 用的 RGBA PNG bytes。
复制 local_test/app.py 的遮罩处理逻辑
1. 加载 image RGB
2. 加载 mask RGBA取所有通道 max 支持红//alpha 遮罩
3. resize mask 到与 image 一致
4. 高斯模糊(radius=4) 柔化边缘
5. alpha = 255 - mask绘制区=255 alpha=0 重绘区
6. 合成 RGBA PNG
"""
image = Image.open(io.BytesIO(image_bytes)).convert("RGB")
mask_img = Image.open(io.BytesIO(mask_bytes)).convert("RGBA")
mask_arr = np.array(mask_img)
mask_data = np.max(mask_arr, axis=2) # (H, W) uint8
mask_data_img = Image.fromarray(mask_data, mode="L")
if mask_data_img.size != image.size:
mask_data_img = mask_data_img.resize(image.size, Image.LANCZOS)
mask_data_img = mask_data_img.filter(ImageFilter.GaussianBlur(radius=4))
# ComfyUI LoadImage: mask = 1.0 - (alpha/255)
# alpha=0 -> mask=1.0 (inpaint), alpha=255 -> mask=0.0 (keep)
comfyui_alpha = Image.eval(mask_data_img, lambda x: 255 - x)
r, g, b = image.split()
rgba = Image.merge("RGBA", (r, g, b, comfyui_alpha))
buf = io.BytesIO()
rgba.save(buf, format="PNG")
return buf.getvalue()
def run_redraw(image_bytes: bytes, mask_bytes: bytes,
prompt: str | None = None, timeout: float = 300.0,
front: bool = False, unet_name: str | None = None) -> bytes:
"""直接调 ComfyUI 重绘 — 替代 local_test /api/generate。
Args:
image_bytes: 人物图片字节JPG/PNG
mask_bytes: 遮罩图片字节支持红//alpha 遮罩格式
prompt: 提示词None 用默认 "填充遮罩区域的头发"
timeout: ComfyUI 超时秒数
front: True 时任务插到 ComfyUI 队列最前接口2 时延敏感路径用
unet_name: None 时切换 Flux 模型 flux-2-klein-9b-Q5_K_M.ggufNone 用工作流默认
Returns:
重绘后的 PNG 图片字节
Raises:
RuntimeError: ComfyUI 执行失败
TimeoutError: ComfyUI 超时
"""
rgba_png = _process_mask_to_rgba(image_bytes, mask_bytes)
return comfyui.run(rgba_png, timeout=timeout, prompt=prompt,
workflow_path=_REPAINT_WORKFLOW, front=front,
unet_name=unet_name)
+294 -39
View File
@@ -14,21 +14,83 @@ from . import constants as C
from . import comfyui
from .face_landmarks import FaceLandmarker
from .face_parsing import FaceParser
from .hairline_2d import sample_hairline, smooth_hairline
from .hairline_2d import (
smooth_hairline, sample_hairline_clamped,
)
from .lift_3d import lift_hairline_to_3d, build_middle_row, assemble_full
from .render import load_ext_mesh, load_texture_rgba, render_hairline_overlay, build_overlay_layer
from .mask import build_inpaint_mask, compose_comfy_rgba, mask_from_curve
from .marker_detect import detect_marker_hairline, path_to_curve_mask
import base64
import io
import logging
logger = logging.getLogger("hair.worker")
# 接口2 女性发型 key → change_hair hair_idchang_*)映射:换发型+Flux-2 整帧重绘用。
# 与接口12 final 的 5 型一一对应。
_FEMALE_KEY_TO_CHANG = {
"ellipse": "chang_tuoyuan", # 椭圆
"flower": "chang_huaban", # 花瓣
"heart": "chang_xinxing", # 心形
"straight": "chang_zhixian", # 直线
"wave": "chang_bolang", # 波浪
}
_REPO = os.path.dirname(os.path.dirname(__file__))
_TEXTURE_DIR = os.path.join(_REPO, "hairline_texture")
_BLACK_TEXTURE_DIR = os.path.join(_REPO, "hairline_texture_black")
# 三接口(接口2女重绘 / 接口2男 / 接口3)统一的 ComfyUI 重绘 prompt。
# 关键:ComfyUI 单卡显存装不下 Flux(7.7G)+qwen CLIP(3.9G) 同驻,靠缓存 CLIP 文本条件避免重载。
# prompt 不同会使缓存失效 → 重载 CLIP 并挤出 Flux(每次 +4s)。三接口用同一字符串即可全程命中。
# 与 app.py 接口2/接口3 的默认 prompt 保持一致;可用 REDRAW_PROMPT 覆盖。
_REDRAW_PROMPT = os.getenv("REDRAW_PROMPT", "填充遮罩区域的头发")
# 接口2 女重绘整条管线(swapHair + ComfyUI)送模型前限边。真实照片常达 1257x1495:
# 全分辨率 ComfyUI 重绘要 13~21s 且激活显存把模型挤出。女性路径含 swapHair(SD WebUI ~5.3s
# 固定地板) + ComfyUI 两段串行。1024 档画质更好但部分大图会踩 12s 线,
# 默认压到 896 兜底(ComfyUI ~4s,女性总耗时 9~11s);追画质可设 REDRAW_MAX_SIDE=1024。
_REDRAW_MAX_SIDE = int(os.getenv("REDRAW_MAX_SIDE", "896"))
def _call_local_redraw(image_png_bytes, mask_png_bytes, timeout=300.0,
max_side=None, unet_name=None, prompt=None):
"""直接调 ComfyUI 重绘(替代原 local_test HTTP 服务)。
final + 纯红遮罩 PNG返回重绘后的 PNG bytes
失败抛异常调用方负责 try/except 跳过
max_side ComfyUI 前长边压到多少像素None 用全局默认 _REDRAW_MAX_SIDE
unet_name None 时切换 Flux 模型None 用工作流内置默认
promptNone 用默认 _REDRAW_PROMPT否则用传入的提示词
"""
from .redraw import run_redraw
eff_side = _REDRAW_MAX_SIDE if max_side is None else max_side
img = cv2.imdecode(np.frombuffer(image_png_bytes, np.uint8), cv2.IMREAD_UNCHANGED)
scale = 1.0
orig_w = orig_h = 0
if img is not None:
orig_h, orig_w = img.shape[:2]
m = max(orig_h, orig_w)
if eff_side > 0 and m > eff_side:
scale = eff_side / float(m)
nw, nh = max(1, round(orig_w * scale)), max(1, round(orig_h * scale))
msk = cv2.imdecode(np.frombuffer(mask_png_bytes, np.uint8), cv2.IMREAD_UNCHANGED)
img_s = cv2.resize(img, (nw, nh), interpolation=cv2.INTER_AREA)
msk_s = cv2.resize(msk, (nw, nh), interpolation=cv2.INTER_NEAREST)
image_png_bytes = cv2.imencode(".png", img_s)[1].tobytes()
mask_png_bytes = cv2.imencode(".png", msk_s)[1].tobytes()
logger.info("接口2女 缩图送 Comfy: %dx%d%dx%d (max_side=%d)",
orig_w, orig_h, nw, nh, eff_side)
# front=True:接口2 时延敏感,插到 ComfyUI 队列最前,避免排在接口3/5 的批量任务后面
out = run_redraw(image_png_bytes, mask_png_bytes, timeout=timeout,
prompt=prompt if prompt is not None else _REDRAW_PROMPT,
front=True, unet_name=unet_name)
if scale < 1.0 and out:
out = _upscale_png_to(out, orig_w, orig_h)
return out
# 发际线贴图档位:middle=默认(hairline_texture/)high/low 各自独立文件夹。
_TEXTURE_DIRS = {
"middle": _TEXTURE_DIR,
@@ -36,9 +98,8 @@ _TEXTURE_DIRS = {
"low": os.path.join(_REPO, "hairline_texture_low"),
}
# ⚠️ 本 worker 是 RTX 5090(sm_120)torch 2.2.2(cu121) 只编到 sm_90CUDA 跑算子会报
# "no kernel image"。SegFormer 默认走 CPU~2.5s/张)。换 torch cu128 后可设 SEG_DEVICE=cuda。
_SEG_DEVICE = os.getenv("SEG_DEVICE", "cpu")
# torch 2.7.1+cu128 已支持 RTX 5090 (sm_120)SegFormer 走 GPU~0.05s/张)
_SEG_DEVICE = os.getenv("SEG_DEVICE", "cuda")
_landmarker = None
_parser = None
@@ -100,13 +161,19 @@ def extract_502(image_bgr: np.ndarray):
def extract_context(image_bgr: np.ndarray):
"""照片(BGR) → {landmarks, parse_map, points, valid}。无人脸返回 None。"""
"""照片(BGR) → {landmarks, parse_map, points, valid}。无人脸返回 None。
发际线几何检测固定用 `sample_hairline_clamped`射线检测 + 头部轮廓钳制
短发/剃光头照片 man_test.jpg中间锚点检测失效时纯射线检测的固定 fallback
偏移会把点顶到头部轮廓外面的背景产生"发际线贴到头部外面"的视觉 bug钳制兜底后
fallback 点不会再跑出头部轮廓正常长发照片结果与旧行为一致
"""
rgb = cv2.cvtColor(image_bgr, cv2.COLOR_BGR2RGB)
landmarks = get_landmarker().detect(rgb)
if landmarks is None:
return None
parse_map = get_parser().parse(rgb)
hairline_2d, valid = sample_hairline(landmarks, parse_map)
hairline_2d, valid = sample_hairline_clamped(landmarks, parse_map)
hairline_2d = smooth_hairline(hairline_2d, valid)
hairline_3d = lift_hairline_to_3d(landmarks, hairline_2d)
middle_3d = build_middle_row(landmarks, hairline_3d)
@@ -140,8 +207,9 @@ def generate_previews(image_bgr: np.ndarray, gender: str):
def generate_grow_results(image_bgr: np.ndarray, gender: str, use_mask: bool = True,
prompt: str = None, hair_styles: list[int] | None = None,
workflow_path: str | None = None):
"""指定发际线类型:预览图(白线) + 生发图(ComfyUI)。
workflow_path: str | None = None,
unet_name: str | None = None):
"""指定发际线类型:发际线透明叠图(白线 RGBA) + 生发图(ComfyUI)。
hair_styles1-indexed 列表指定生成哪几张发际线按贴图排序female: 1..5male: 1..4
None 时生成全部兼容旧调用
@@ -149,7 +217,8 @@ def generate_grow_results(image_bgr: np.ndarray, gender: str, use_mask: bool = T
False 时用**干净原图 + 空遮罩** ComfyUI不烧黑色模板线
prompt默认 NoneComfyUI 提示词 None 时替换工作流节点60文本
workflow_path默认 NoneComfyUI 工作流 JSON 路径None 用默认 add_hair.json
Returns: list[dict] {"hairline_type","order","image_bgr"(预览), "grown_png"(bytes None)}
Returns: list[dict] {"hairline_type","order","overlay"((H,W,4) RGBA 透明层),
"grown_png"(bytes None)}
无人脸返回 None某张 ComfyUI 失败时该项 grown_png=None不抛异常
"""
if gender not in ("male", "female"):
@@ -170,16 +239,23 @@ def generate_grow_results(image_bgr: np.ndarray, gender: str, use_mask: bool = T
if not use_mask:
try:
h, w = image_bgr.shape[:2]
img_s, msk_s, gsc = _prep_comfy_input(image_bgr, np.zeros((h, w), np.uint8))
buf = io.BytesIO()
compose_comfy_rgba(image_bgr, np.zeros((h, w), np.uint8)).save(buf, format="PNG")
shared_grown = comfyui.run(buf.getvalue(), prompt=prompt, workflow_path=workflow_path)
compose_comfy_rgba(img_s, msk_s).save(buf, format="PNG", compress_level=1)
# front=True:接口2 时延敏感,插到 ComfyUI 队列最前
shared_grown = comfyui.run(buf.getvalue(), prompt=prompt,
workflow_path=workflow_path, front=True,
unet_name=unet_name)
if gsc < 1.0 and shared_grown:
shared_grown = _upscale_png_to(shared_grown, w, h)
except Exception as e: # noqa: BLE001
logger.warning("接口2 生发图失败(无遮罩)%s", e)
results = []
h, w = image_bgr.shape[:2]
for order, (key, white_path) in items:
white = load_texture_rgba(white_path)
preview = render_hairline_overlay(image_bgr, ctx["points"], ext_faces, uv, white)
overlay = build_overlay_layer(h, w, ctx["points"], ext_faces, uv, white)
if not use_mask:
grown_png = shared_grown
@@ -189,14 +265,124 @@ def generate_grow_results(image_bgr: np.ndarray, gender: str, use_mask: bool = T
black = load_texture_rgba(_black_texture_path(white_path))
marked, mask = build_inpaint_mask(
image_bgr, ctx["landmarks"], ctx["parse_map"], ctx["points"], black)
m_s, msk_s, gsc = _prep_comfy_input(marked, mask)
buf = io.BytesIO()
compose_comfy_rgba(marked, mask).save(buf, format="PNG")
grown_png = comfyui.run(buf.getvalue(), prompt=prompt, workflow_path=workflow_path)
compose_comfy_rgba(m_s, msk_s).save(buf, format="PNG", compress_level=1)
# front=True:接口2 时延敏感,插到 ComfyUI 队列最前
grown_png = comfyui.run(buf.getvalue(), prompt=prompt,
workflow_path=workflow_path, front=True,
unet_name=unet_name)
if gsc < 1.0 and grown_png:
grown_png = _upscale_png_to(grown_png, w, h)
except Exception as e: # noqa: BLE001 单张失败不拖垮整请求
logger.warning("接口2 生发图失败 type=%s%s", key, e)
results.append({"hairline_type": key, "order": order,
"image_bgr": preview, "grown_png": grown_png})
"overlay": overlay, "grown_png": grown_png})
return results
def generate_grow_results_swap(image_bgr: np.ndarray, hair_styles: list[int] | None,
redraw_defaults: dict,
redraw_max_side: int | None = None,
unet_name: str | None = None):
"""接口2 女性专用:发际线透明叠图(同 generate_grow_results+ 换发型重绘图。
grown 图来源新流程对每个选中发型把 female key 映射到 change_hair chang_* hair_id
face_analysis.hairline_grow.generate_hairline_redraw= 接口12 final 管线参数用
redraw_defaults拿到 final接缝融合基底+ - 纯红遮罩 PNG**后端直接调
ComfyUI**0716add-hair-api.json 工作流完成发际线带重绘重绘结果作为生发图
overlay 仍是发际线曲线透明层 generate_grow_results 完全一致
Returns: list[dict] {"hairline_type","order","overlay","grown_png"(jpg bytes None)}
无人脸返回 None单个发型换发型/重绘失败时 grown_png=None不抛异常
"""
from face_analysis.hairline_grow import generate_hairline_redraw, NoFaceError
from face_analysis.head_mask import SEGFORMER_HAIR
ctx = extract_context(image_bgr)
if ctx is None:
return None
uv, ext_faces = load_ext_mesh()
# 复用 extract_context 已算好的 SegFormer parse_map,避免 generate_hairline_redraw 内部重复分割
hair_mask_reuse = (ctx["parse_map"] == SEGFORMER_HAIR)
textures = get_texture_map()["female"] # [(key, path), ...] 已排序
if hair_styles is not None:
items = [(s, textures[s - 1]) for s in hair_styles]
else:
items = list(enumerate(textures, start=1))
results = []
h, w = image_bgr.shape[:2]
# 重绘管线(swapHair + ComfyUI)统一降分辨率:真实照片 swap(SD WebUI)~5s、blend、ComfyUI
# 均随分辨率线性下降。overlay 预览仍用全分辨率;grown_png 最后放大回原尺寸。
eff_side = _REDRAW_MAX_SIDE if redraw_max_side is None else redraw_max_side
redraw_img = image_bgr
hair_mask_redraw = hair_mask_reuse
if eff_side > 0 and max(h, w) > eff_side:
redraw_img, _rs = _downscale_max_side(image_bgr, eff_side)
_nh, _nw = redraw_img.shape[:2]
if hair_mask_redraw is not None:
hair_mask_redraw = cv2.resize(hair_mask_reuse.astype(np.uint8), (_nw, _nh),
interpolation=cv2.INTER_NEAREST).astype(bool)
logger.info("接口2女 管线降分辨率: %dx%d%dx%d (max_side=%d)",
w, h, _nw, _nh, eff_side)
for order, (key, white_path) in items:
white = load_texture_rgba(white_path)
overlay = build_overlay_layer(h, w, ctx["points"], ext_faces, uv, white)
grown_png = None
chang_id = _FEMALE_KEY_TO_CHANG.get(key)
if chang_id is None:
logger.warning("接口2 换发型:female key=%s 无对应 chang_id,跳过生发图", key)
else:
try:
import time as _t
_ts0 = _t.perf_counter()
data = generate_hairline_redraw(redraw_img, chang_id, hair_mask=hair_mask_redraw, **redraw_defaults)
_ts1 = _t.perf_counter()
steps = data.get("steps") or {}
# ④ final(接缝融合基底)+ ⑤-② 纯红遮罩 PNG
final_b64 = steps.get("final_base64") or ""
mask_b64 = steps.get("redraw_band_mask_base64") or ""
if not final_b64 or not mask_b64:
logger.warning("接口2 换发型:type=%s final/遮罩缺失(final=%d mask=%d",
key, len(final_b64), len(mask_b64))
else:
# 去掉 data URI 前缀
if final_b64.startswith("data:"):
final_b64 = final_b64.split(",", 1)[1]
if mask_b64.startswith("data:"):
mask_b64 = mask_b64.split(",", 1)[1]
final_bytes = base64.b64decode(final_b64)
mask_bytes = base64.b64decode(mask_b64)
# 后端直接调 ComfyUI 重绘,返回重绘后的 PNG
_tr0 = _t.perf_counter()
grown_png = _call_local_redraw(final_bytes, mask_bytes,
max_side=redraw_max_side,
unet_name=unet_name)
_tr1 = _t.perf_counter()
_tm = data.get("timings_ms") or {}
logger.info("接口2女 分段计时 type=%s: swapHair管线=%.2fs (mask=%dms swap=%dms blend=%dms), ComfyUI重绘=%.2fs",
key, _ts1 - _ts0,
_tm.get("mask", 0), _tm.get("swap", 0), _tm.get("blend", 0),
_tr1 - _tr0)
if grown_png is None:
logger.warning("接口2 换发型:type=%s 重绘结果为空", key)
elif redraw_img is not image_bgr:
# 管线在降分辨率图上跑,结果放大回原尺寸
grown_png = _upscale_png_to(grown_png, w, h)
except NoFaceError:
logger.warning("接口2 换发型:type=%s 未检出人脸", key)
except Exception as e: # noqa: BLE001 单张失败不拖垮整请求
logger.warning("接口2 换发型图失败 type=%s%s", key, e)
results.append({"hairline_type": key, "order": order,
"overlay": overlay, "grown_png": grown_png})
return results
@@ -216,7 +402,7 @@ def _grow_from_texture(image_bgr: np.ndarray, ctx: dict, white_path: str | None,
h, w = image_bgr.shape[:2]
marked, mask = image_bgr, np.zeros((h, w), np.uint8)
buf = io.BytesIO()
compose_comfy_rgba(marked, mask).save(buf, format="PNG")
compose_comfy_rgba(marked, mask).save(buf, format="PNG", compress_level=1)
return comfyui.run(buf.getvalue(), prompt=prompt)
except Exception as e: # noqa: BLE001 单张失败不拖垮整请求
logger.warning("接口5 生发图失败:%s", e)
@@ -225,15 +411,19 @@ def _grow_from_texture(image_bgr: np.ndarray, ctx: dict, white_path: str | None,
def generate_hairline_pngs(image_bgr: np.ndarray, gender: str,
hair_styles: list[int], use_mask: bool = True,
prompt: str | None = None):
"""接口5:对选中发型返回 middle/high/low 三档发际线叠图 + 生发图(同接口2)。
prompt: str | None = None,
generate_grow_image: bool = True):
"""接口5:对选中发型返回 middle/high/low 三档发际线透明叠图 + 生发图(同接口2)。
入参同接口2先选 gender再多选 hair_styles必填1-indexed 按贴图排序
每个选中发型返回三档叠图middle/high/low与一张生发图三档贴图同名
生发黑模板固定取自 hairline_texture_black/middle故生发目标固定 middle
每个选中发型返回三档叠图middle/high/lowRGBA 透明层只含发际线曲线与一张生发图
三档贴图同名生发黑模板固定取自 hairline_texture_black/middle故生发目标固定 middle
use_mask/prompt同接口2 的生发参数
Returns: {"images":[{hairline_type,order,overlays:{middle,high,low}(BGR),grown_png}],
"best_center":(x,y)}无人脸 Nonebest_center 取首个选中发型的 middle
generate_grow_image默认 True是否生成生发图ComfyUI最耗时False 时跳过生发
各发型 grown_png 恒为 None可大幅降低耗时仅留三档发际线叠图与中心点
Returns: {"images":[{hairline_type,order,overlays:{middle,high,low}((H,W,4) RGBA 透明层),grown_png}],
"best_centers":{"middle":(x,y),"high":(x,y),"low":(x,y)}}无人脸 None
best_centers 取首个选中发型三档各自的发际线中点
"""
if gender not in ("male", "female"):
raise ValueError(f"gender 必须是 male/female,收到 {gender!r}")
@@ -252,32 +442,84 @@ def generate_hairline_pngs(image_bgr: np.ndarray, gender: str,
tex_by_level = {lv: get_texture_map(lv)[gender] for lv in _TEXTURE_DIRS}
# use_mask=False:干净原图+空遮罩与贴图无关,只跑一次 ComfyUI,选中项复用
# generate_grow_image=False:完全跳过生发(最耗时),grown_png 恒为 None
shared_grown = None
if not use_mask:
if generate_grow_image and not use_mask:
shared_grown = _grow_from_texture(image_bgr, ctx, None, use_mask=False, prompt=prompt)
images, best_center = [], None
def _center_of(overlay):
"""从某档发际线透明叠图取面部中轴处的发际线中点 (x,y),无像素返回 None。"""
ys, xs = np.where(overlay[:, :, 3] > 40)
if not xs.size:
return None
near = np.abs(xs - face_cx) <= max(2, int(w * 0.02))
col_ys = ys[near] if near.any() else ys[np.argsort(np.abs(xs - face_cx))[:20]]
return (int(round(face_cx)), int(round(float(col_ys.mean()))))
images, best_centers = [], None
for s in hair_styles: # s = 1-indexed 发型序号
key, mid_path = tex_by_level["middle"][s - 1]
overlays = {}
for lv in _TEXTURE_DIRS:
white = load_texture_rgba(tex_by_level[lv][s - 1][1])
overlays[lv] = render_hairline_overlay(image_bgr, ctx["points"], ext_faces, uv, white)
# 生发:固定 middle 黑模板
grown_png = shared_grown if not use_mask else \
_grow_from_texture(image_bgr, ctx, mid_path, use_mask=True, prompt=prompt)
overlays[lv] = build_overlay_layer(h, w, ctx["points"], ext_faces, uv, white)
# 生发:固定 middle 黑模板generate_grow_image=False 时跳过,恒 None
if not generate_grow_image:
grown_png = None
elif not use_mask:
grown_png = shared_grown
else:
grown_png = _grow_from_texture(image_bgr, ctx, mid_path, use_mask=True, prompt=prompt)
images.append({"hairline_type": key, "order": s,
"overlays": overlays, "grown_png": grown_png})
# best_center:首个选中发型middle 档发际线中点(面部中轴处的发际线 y)
if best_center is None:
white = load_texture_rgba(mid_path)
overlay = build_overlay_layer(h, w, ctx["points"], ext_faces, uv, white)
ys, xs = np.where(overlay[:, :, 3] > 40)
if xs.size:
near = np.abs(xs - face_cx) <= max(2, int(w * 0.02))
col_ys = ys[near] if near.any() else ys[np.argsort(np.abs(xs - face_cx))[:20]]
best_center = (int(round(face_cx)), int(round(float(col_ys.mean()))))
return {"images": images, "best_center": best_center}
# best_centers:首个选中发型三档(middle/high/low)发际线中点
if best_centers is None:
best_centers = {lv: _center_of(overlays[lv]) for lv in _TEXTURE_DIRS}
return {"images": images, "best_centers": best_centers}
# 接口3 送 ComfyUI 前限边,降低峰值显存,避免与接口2 切换时把 Flux 挤出。
# 统一 prompt 后 Flux 不再被 CLIP 挤出,接口3 可用较高分辨率。可用 GROW_B_MAX_SIDE 覆盖。
_GROW_B_MAX_SIDE = int(os.getenv("GROW_B_MAX_SIDE", "1024"))
def _downscale_max_side(img_bgr: np.ndarray, max_side: int) -> tuple[np.ndarray, float]:
"""长边超过 max_side 时等比例缩小;返回 (图, scale)scale=新/旧。"""
h, w = img_bgr.shape[:2]
m = max(h, w)
if max_side <= 0 or m <= max_side:
return img_bgr, 1.0
scale = max_side / float(m)
nw = max(1, int(round(w * scale)))
nh = max(1, int(round(h * scale)))
out = cv2.resize(img_bgr, (nw, nh), interpolation=cv2.INTER_AREA)
return out, scale
def _upscale_png_to(png_bytes: bytes, out_w: int, out_h: int) -> bytes:
"""把 Comfy 输出 PNG 双线性拉回原图尺寸(仅展示对齐,不增加推理细节)。"""
arr = np.frombuffer(png_bytes, np.uint8)
img = cv2.imdecode(arr, cv2.IMREAD_UNCHANGED)
if img is None:
return png_bytes
if img.shape[1] == out_w and img.shape[0] == out_h:
return png_bytes
resized = cv2.resize(img, (out_w, out_h), interpolation=cv2.INTER_LINEAR)
ok, buf = cv2.imencode(".png", resized)
return buf.tobytes() if ok else png_bytes
def _prep_comfy_input(img_bgr: np.ndarray, mask: np.ndarray) -> tuple[np.ndarray, np.ndarray, float]:
"""单段 ComfyUI 生发(接口2男 / 接口3)送图前限边到 GROW_B_MAX_SIDE。
返回 (缩后图, 缩后遮罩, scale)scale<1 时调用方需把结果放大回原尺寸"""
h, w = img_bgr.shape[:2]
if _GROW_B_MAX_SIDE <= 0 or max(h, w) <= _GROW_B_MAX_SIDE:
return img_bgr, mask, 1.0
out, scale = _downscale_max_side(img_bgr, _GROW_B_MAX_SIDE)
nh, nw = out.shape[:2]
msk = cv2.resize(mask, (nw, nh), interpolation=cv2.INTER_NEAREST)
logger.info("接口2男/接口3 缩图送 Comfy: %dx%d%dx%d (max_side=%d)",
w, h, nw, nh, _GROW_B_MAX_SIDE)
return out, msk, scale
def generate_grow_b(marked_bgr: np.ndarray, use_mask: bool = True, prompt: str = None):
@@ -286,12 +528,23 @@ def generate_grow_b(marked_bgr: np.ndarray, use_mask: bool = True, prompt: str =
检测路径只用来**建遮罩**ComfyUI 输入图用 **marked 原图**含医生手绘线
工作流提示词会清除黑线再生发
Comfy 前若长边 > GROW_B_MAX_SIDE默认 896会先等比例缩小降低峰值显存
输出再拉回原图尺寸
use_mask默认 True是否启用自动检测的遮罩用于测试对比
- True检测手绘线 建遮罩 alpha=255mask透明区=重绘区节点44 画黄色参考区
- False跳过检测直接送划线图alpha 255空遮罩节点26 mask 为空
模型仅凭医生黑线参考生发无需改工作流唯一变量是遮罩
Returns: {"grown_png": bytes None, "status": "ok"|"no_face"|"no_line"}
"""
orig_h, orig_w = marked_bgr.shape[:2]
marked_bgr, _scale = _downscale_max_side(marked_bgr, _GROW_B_MAX_SIDE)
if _scale < 1.0:
logger.info(
"接口3 缩图送 Comfy: %dx%d%dx%d (max_side=%d)",
orig_w, orig_h, marked_bgr.shape[1], marked_bgr.shape[0], _GROW_B_MAX_SIDE,
)
h, w = marked_bgr.shape[:2]
if use_mask:
rgb = cv2.cvtColor(marked_bgr, cv2.COLOR_BGR2RGB)
@@ -309,8 +562,10 @@ def generate_grow_b(marked_bgr: np.ndarray, use_mask: bool = True, prompt: str =
mask = np.zeros((h, w), np.uint8) # 空遮罩:alpha 全 255,跳过检测
buf = io.BytesIO()
compose_comfy_rgba(marked_bgr, mask).save(buf, format="PNG") # marked 原图 + 遮罩
compose_comfy_rgba(marked_bgr, mask).save(buf, format="PNG", compress_level=1) # marked + 遮罩
grown_png = comfyui.run(buf.getvalue(), prompt=prompt)
if _scale < 1.0 and grown_png:
grown_png = _upscale_png_to(grown_png, orig_w, orig_h)
return {"grown_png": grown_png, "status": "ok"}
BIN
View File
Binary file not shown.

After

Width:  |  Height:  |  Size: 440 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 243 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 147 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 198 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 223 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 174 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 180 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 184 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 198 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 186 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 176 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 175 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 243 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 156 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 156 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 109 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 104 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 117 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 156 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 250 KiB

BIN
View File
Binary file not shown.

After

Width:  |  Height:  |  Size: 459 KiB

+174
View File
@@ -0,0 +1,174 @@
# 发型补全服务 API 文档
## 服务概述
本服务提供基于 ComfyUI 的发型补全(局部重绘)能力。通过传入人物图片和遮罩图片,调用 ComfyUI 工作流(`0716add-hair.json`)生成补全后的图片。
## 技术栈
- **框架**: Flask
- **依赖**: requests, Pillow, numpy
- **后端**: ComfyUI (http://127.0.0.1:8188)
## 服务地址
- **HTTP**: `http://127.0.0.1:8899`
- **前端页面**: `http://127.0.0.1:8899/`
- **API接口**: `http://127.0.0.1:8899/api/generate`
## 启动方式
### 使用脚本(推荐)
```bash
# 启动服务
cd /home/ubuntu/hair/local_test
./start.sh
# 停止服务
./stop.sh
```
### 直接运行
```bash
cd /home/ubuntu/hair/local_test
/home/ubuntu/ComfyUI/venv/bin/python app.py
```
## API 接口
### POST /api/generate
调用 ComfyUI 工作流,传入图片和遮罩,返回生成结果。
#### 请求参数
| 参数名 | 类型 | 必填 | 说明 |
|--------|------|------|------|
| image | File | 是 | 人物图片(支持 jpg, png 等常见格式) |
| mask | File | 是 | 遮罩图片(支持 jpg, png,遮罩区域可用红色/白色/alpha 通道标识) |
| prompt | String | 否 | 提示词,默认值:"填充遮罩区域的头发" |
#### 遮罩图片格式说明
服务支持多种遮罩格式,自动提取遮罩区域:
| 格式类型 | 示例 | 遮罩区域标识 |
|----------|------|--------------|
| 红色遮罩 | 红色画笔绘制 | R=255 的像素 |
| 白色遮罩 | 白色画笔绘制 | R=G=B=255 的像素 |
| Alpha 遮罩 | 透明背景 | A=255 的像素 |
服务会取所有通道的最大值作为遮罩强度,因此以上格式均可混用。
**注意**: 遮罩区域表示需要重绘的部分,非遮罩区域保持原图不变。
#### 请求示例(curl
```bash
curl -X POST http://127.0.0.1:8899/api/generate \
-F "image=@/path/to/person.jpg" \
-F "mask=@/path/to/mask.png" \
-F "prompt=填充遮罩区域的头发" \
--output result.png
```
#### 请求示例(Python
```python
import requests
url = "http://127.0.0.1:8899/api/generate"
files = {
"image": open("person.jpg", "rb"),
"mask": open("mask.png", "rb"),
}
data = {
"prompt": "填充遮罩区域的头发"
}
resp = requests.post(url, files=files, data=data, timeout=600)
if resp.status_code == 200:
with open("result.png", "wb") as f:
f.write(resp.content)
else:
print(f"Error: {resp.json()}")
```
#### 响应
**成功 (HTTP 200)**:
返回 PNG 图片二进制数据,Content-Type: `image/png`
**失败 (HTTP 4xx/5xx)**:
返回 JSON 格式错误信息:
```json
{
"error": "错误描述"
}
```
#### 错误码
| 状态码 | 说明 |
|--------|------|
| 500 | 内部错误(文件处理失败、ComfyUI 返回错误等) |
| 503 | 无法连接到 ComfyUI(服务未启动或端口错误) |
| 500 | 超时(工作流执行超过 5 分钟) |
## 工作流说明
服务使用的工作流 `0716add-hair.json` 包含以下处理步骤:
1. **加载模型**: Flux 2 Klein 9B (FP8) + Qwen 3.8B CLIP
2. **图片上传**: 将原图与遮罩合成为 RGBA 格式上传至 ComfyUI
3. **遮罩处理**: 填充孔洞 → 转换为图像 → 缩放 → 转换回遮罩
4. **图像缩放**: 按比例缩放至合适尺寸(最大边长 1024,8 的倍数)
5. **VAE 编码**: 将图像编码为 latent
6. **采样生成**: 使用 Flux 模型 + ReferenceLatent 进行局部重绘
7. **VAE 解码**: 将 latent 解码为图像
8. **颜色匹配**: 使用 ColorMatch 保持颜色一致
9. **保存结果**: 返回生成的图片
## 前置依赖
启动服务前需确保:
1. **ComfyUI 已启动**: `http://127.0.0.1:8188` 可访问
2. **模型文件存在**:
- `models/unet/flux2.0/flux-2-klein-9b-fp8.safetensors`
- `models/vae/flux2-vae.safetensors`
- `models/clip/qwen_3_8b_fp8mixed.safetensors`
3. **虚拟环境已激活**: 使用 `/home/ubuntu/ComfyUI/venv/bin/python`
## 文件结构
```
/home/ubuntu/hair/local_test/
├── app.py # Flask 后端服务
├── index.html # 前端测试页面
├── test_api.py # API 测试脚本
├── README.md # 本文档
├── output/ # 测试结果输出目录
├── 用来重绘.jpg # 测试人物图片
└── 用来重绘.png # 测试遮罩图片
```
## 使用流程
1. 启动 ComfyUI`python main.py --listen`
2. 启动本服务(`python app.py`
3. 调用 API 或访问前端页面上传图片和遮罩
4. 等待生成完成(通常 30-60 秒)
5. 获取返回的 PNG 图片
## 注意事项
- 请求超时时间为 5 分钟,生成复杂图片可能需要较长时间
- 遮罩图片尺寸需与人物图片一致,服务会自动缩放对齐
- 建议使用红色或白色绘制遮罩,确保遮罩强度足够
- 服务会自动对遮罩边缘进行高斯模糊(radius=4),避免硬边
+339
View File
@@ -0,0 +1,339 @@
#!/usr/bin/env python3
"""Hair inpainting service - calls ComfyUI workflow with image + mask."""
import io
import json
import time
import random
import logging
import traceback
import requests
from flask import Flask, request, jsonify, send_file
import numpy as np
from PIL import Image, ImageFilter
# 让 PIL 支持 iPhone 的 HEIC/HEIF 照片(浏览器 accept="image/*" 会允许选中它们)。
try:
from pillow_heif import register_heif_opener
register_heif_opener()
_HEIF_OK = True
except Exception:
_HEIF_OK = False
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s [%(levelname)s] %(message)s",
)
log = logging.getLogger("hair")
app = Flask(__name__)
COMFYUI_URL = "http://127.0.0.1:8188"
# 允许浏览器跨域直连本服务(如 hair 项目的测试页)。
# 不引入 flask-cors 依赖,直接在响应头 + OPTIONS 预检里处理。
_CORS_HEADERS = {
"Access-Control-Allow-Origin": "*",
"Access-Control-Allow-Methods": "POST, OPTIONS",
"Access-Control-Allow-Headers": "Content-Type",
"Access-Control-Expose-Headers": "X-Generate-Time",
}
@app.after_request
def _add_cors(resp):
for k, v in _CORS_HEADERS.items():
resp.headers[k] = v
return resp
@app.route("/api/generate", methods=["OPTIONS"])
def _generate_preflight():
"""CORS 预检:浏览器 POST 前会先发 OPTIONS。"""
return ("", 204)
def build_workflow(image_filename, prompt_text, seed=None):
"""Build ComfyUI API workflow from the 0716add-hair.json structure."""
if seed is None:
seed = random.randint(0, 2**53)
return {
# Loaders
"16": {"class_type": "UNETLoader", "inputs": {
"unet_name": "flux2.0/flux-2-klein-9b-fp8.safetensors",
"weight_dtype": "fp8_e4m3fn_fast"}},
"3": {"class_type": "VAELoader", "inputs": {
"vae_name": "flux2-vae.safetensors"}},
"61": {"class_type": "CLIPLoader", "inputs": {
"clip_name": "qwen_3_8b_fp8mixed.safetensors",
"type": "flux2",
"device": "default"}},
# Input image (with mask in alpha channel)
"26": {"class_type": "LoadImage", "inputs": {
"image": image_filename}},
# Prompt
"60": {"class_type": "JjkText", "inputs": {
"text": prompt_text}},
"22": {"class_type": "CLIPTextEncode", "inputs": {
"clip": ["61", 0],
"text": ["60", 0]}},
# Image size
"31": {"class_type": "easy imageSize", "inputs": {
"image": ["26", 0]}},
# Mask processing: fill holes -> convert to image -> scale -> back to mask
"33": {"class_type": "Mask Fill Holes", "inputs": {
"masks": ["26", 1]}},
"36": {"class_type": "Convert Masks to Images", "inputs": {
"masks": ["33", 0]}},
"39": {"class_type": "ImageScale", "inputs": {
"image": ["36", 0],
"upscale_method": "nearest-exact",
"width": ["31", 0],
"height": ["31", 1],
"crop": "disabled"}},
"37": {"class_type": "Image To Mask", "inputs": {
"image": ["39", 0],
"method": "intensity"}},
# Scale image+mask by aspect ratio
"32": {"class_type": "LayerUtility: ImageScaleByAspectRatio V2", "inputs": {
"image": ["26", 0],
"mask": ["37", 0],
"aspect_ratio": "custom",
"proportional_width": ["31", 0],
"proportional_height": ["31", 1],
"fit": "letterbox",
"method": "lanczos",
"round_to_multiple": "8",
"scale_to_side": "None",
"scale_to_length": 1024,
"background_color": "#000000"}},
# Preview (pass_through=true, just passes the image through)
"44": {"class_type": "ImageAndMaskPreview", "inputs": {
"image": ["32", 0],
"mask": ["32", 1],
"mask_opacity": 1,
"mask_color": "FFFF00",
"pass_through": True}},
# Get size of scaled image
"14": {"class_type": "GetImageSize+", "inputs": {
"image": ["44", 0]}},
# VAE encode the image
"13": {"class_type": "VAEEncode", "inputs": {
"pixels": ["44", 0],
"vae": ["3", 0]}},
# Flux model setup
"2": {"class_type": "ModelSamplingFlux", "inputs": {
"model": ["16", 0],
"max_shift": 1.15,
"base_shift": 0.5,
"width": ["14", 0],
"height": ["14", 1]}},
"19": {"class_type": "FluxGuidance", "inputs": {
"conditioning": ["22", 0],
"guidance": 1}},
"5": {"class_type": "ReferenceLatent", "inputs": {
"conditioning": ["19", 0],
"latent": ["13", 0]}},
# Empty latent for sampling
"7": {"class_type": "EmptySD3LatentImage", "inputs": {
"width": ["14", 0],
"height": ["14", 1],
"batch_size": 1}},
# Scheduler & guider
"1": {"class_type": "BasicScheduler", "inputs": {
"model": ["2", 0],
"scheduler": "simple",
"steps": 4,
"denoise": 1}},
"20": {"class_type": "BasicGuider", "inputs": {
"model": ["2", 0],
"conditioning": ["5", 0]}},
# Noise & sampler
"6": {"class_type": "RandomNoise", "inputs": {
"noise_seed": seed}},
"8": {"class_type": "KSamplerSelect", "inputs": {
"sampler_name": "euler"}},
"9": {"class_type": "SamplerCustomAdvanced", "inputs": {
"noise": ["6", 0],
"guider": ["20", 0],
"sampler": ["8", 0],
"sigmas": ["1", 0],
"latent_image": ["7", 0]}},
# VAE decode
"10": {"class_type": "VAEDecode", "inputs": {
"samples": ["9", 0],
"vae": ["3", 0]}},
# Color match with original image
"62": {"class_type": "ColorMatch", "inputs": {
"image_ref": ["26", 0],
"image_target": ["10", 0],
"method": "mkl",
"strength": 1,
"multithread": True}},
# Save result
"17": {"class_type": "SaveImage", "inputs": {
"images": ["62", 0],
"filename_prefix": "hair_inpaint"}},
}
@app.route("/")
def index():
return send_file("index.html")
@app.route("/api/generate", methods=["POST"])
def generate():
t_start = time.time()
try:
if "image" not in request.files or "mask" not in request.files:
msg = f"缺少上传文件: files={list(request.files.keys())}"
log.warning(msg)
return jsonify({"error": msg}), 400
image_file = request.files["image"]
mask_file = request.files["mask"]
prompt_text = request.form.get("prompt", "填充遮罩区域的头发")
log.info(
"收到请求: image=%s mask=%s prompt=%r",
image_file.filename, mask_file.filename, prompt_text,
)
# Load original image as RGB
try:
image = Image.open(image_file).convert("RGB")
except Exception as e:
log.error("无法解码人物图片 %s: %s", image_file.filename, e)
hint = "" if _HEIF_OK else "(当前不支持 HEIC"
return jsonify({
"error": f"无法识别人物图片格式{hint},请改用 JPG/PNG: {e}"
}), 400
# Load mask and extract mask data from ALL channels (R, G, B, A)
# This handles different mask formats:
# - Red mask (R=255 where drawn): user-provided PNG
# - White mask (R=G=B=255 where drawn): frontend canvas
# - Alpha mask (A=255 where drawn): transparent brush
try:
mask_img = Image.open(mask_file).convert("RGBA")
except Exception as e:
log.error("无法解码遮罩图片 %s: %s", mask_file.filename, e)
return jsonify({
"error": f"无法识别遮罩图片格式,请改用 JPG/PNG: {e}"
}), 400
mask_arr = np.array(mask_img)
# Use max of all channels: 255 where any color/alpha is drawn, 0 where empty
mask_data = np.max(mask_arr, axis=2) # (H, W) uint8
# Ensure mask matches image size
mask_data_img = Image.fromarray(mask_data, mode="L")
if mask_data_img.size != image.size:
mask_data_img = mask_data_img.resize(image.size, Image.LANCZOS)
# Apply slight blur for soft edges (similar to ComfyUI's brush)
mask_data_img = mask_data_img.filter(ImageFilter.GaussianBlur(radius=4))
# ComfyUI LoadImage: mask = 1.0 - (alpha/255)
# So alpha=0 -> mask=1.0 (inpaint), alpha=255 -> mask=0.0 (keep)
# We want: drawn area (mask_data=255) -> inpaint -> alpha=0
# undrawn area (mask_data=0) -> keep -> alpha=255
comfyui_alpha = Image.eval(mask_data_img, lambda x: 255 - x)
# Combine into RGBA (split RGB into separate channels first)
r, g, b = image.split()
rgba = Image.merge("RGBA", (r, g, b, comfyui_alpha))
# Upload to ComfyUI
img_bytes = io.BytesIO()
rgba.save(img_bytes, format="PNG")
img_bytes.seek(0)
upload_resp = requests.post(
f"{COMFYUI_URL}/upload/image",
files={"image": ("hair_input.png", img_bytes, "image/png")},
timeout=30,
)
upload_data = upload_resp.json()
if "name" not in upload_data:
log.error("ComfyUI 上传图片失败: %s", upload_data)
return jsonify({"error": f"Upload failed: {upload_data}"}), 500
image_filename = upload_data["name"]
# Build and queue workflow
workflow = build_workflow(image_filename, prompt_text)
prompt_resp = requests.post(
f"{COMFYUI_URL}/prompt",
json={"prompt": workflow},
timeout=30,
)
prompt_data = prompt_resp.json()
if "error" in prompt_data:
log.error(
"ComfyUI /prompt 校验失败: error=%s node_errors=%s",
prompt_data.get("error"), prompt_data.get("node_errors"),
)
return jsonify({"error": json.dumps(prompt_data["error"], ensure_ascii=False)}), 500
prompt_id = prompt_data["prompt_id"]
# Poll for completion (5 min timeout, 0.1s interval)
for _ in range(3000):
time.sleep(0.1)
history_resp = requests.get(
f"{COMFYUI_URL}/history/{prompt_id}", timeout=10
)
history_data = history_resp.json()
if prompt_id in history_data:
status = history_data[prompt_id].get("status", {})
if status.get("status_str") == "error":
log.error(
"ComfyUI 工作流执行失败: %s",
json.dumps(status, ensure_ascii=False),
)
return jsonify({
"error": "Workflow execution failed",
"detail": status.get("messages", status),
}), 500
outputs = history_data[prompt_id].get("outputs", {})
if "17" in outputs: # SaveImage node
image_info = outputs["17"]["images"][0]
filename = image_info["filename"]
subfolder = image_info.get("subfolder", "")
img_type = image_info.get("type", "output")
view_resp = requests.get(
f"{COMFYUI_URL}/view",
params={"filename": filename, "subfolder": subfolder, "type": img_type},
timeout=30,
)
elapsed = time.time() - t_start
log.info("重绘完成,服务端耗时 %.2fs", elapsed)
resp = send_file(
io.BytesIO(view_resp.content), mimetype="image/png"
)
resp.headers["X-Generate-Time"] = f"{elapsed:.2f}"
return resp
return jsonify({"error": "Timeout: workflow did not complete in 5 minutes"}), 500
except requests.ConnectionError:
log.error("无法连接 ComfyUI @ %s", COMFYUI_URL)
return jsonify({"error": "Cannot connect to ComfyUI at " + COMFYUI_URL + ". Is it running?"}), 503
except Exception as e:
log.error("生成失败,未捕获异常:\n%s", traceback.format_exc())
return jsonify({"error": f"{type(e).__name__}: {e}"}), 500
if __name__ == "__main__":
app.run(host="0.0.0.0", port=8899, debug=False)
+77
View File
@@ -0,0 +1,77 @@
#!/usr/bin/env python3
"""Benchmark ComfyUI hair-inpaint workflow across model / dtype / steps."""
import io, time, sys
import requests
import numpy as np
from PIL import Image, ImageFilter
import app as A
COMFY = "http://127.0.0.1:8188"
def prep_and_upload():
image = Image.open("用来重绘.jpg").convert("RGB")
mask_img = Image.open("用来重绘.png").convert("RGBA")
mask_data = np.max(np.array(mask_img), axis=2)
m = Image.fromarray(mask_data, mode="L")
if m.size != image.size:
m = m.resize(image.size, Image.LANCZOS)
m = m.filter(ImageFilter.GaussianBlur(radius=4))
alpha = Image.eval(m, lambda x: 255 - x)
r, g, b = image.split()
rgba = Image.merge("RGBA", (r, g, b, alpha))
buf = io.BytesIO(); rgba.save(buf, format="PNG"); buf.seek(0)
up = requests.post(f"{COMFY}/upload/image",
files={"image": ("hair_input.png", buf, "image/png")}).json()
return up["name"]
def run_once(fname, model, dtype, steps):
wf = A.build_workflow(fname, "填充遮罩区域的头发")
wf["16"]["inputs"]["unet_name"] = model
wf["16"]["inputs"]["weight_dtype"] = dtype
wf["1"]["inputs"]["steps"] = steps
r = requests.post(f"{COMFY}/prompt", json={"prompt": wf}).json()
if "prompt_id" not in r:
raise RuntimeError(f"submit failed: {str(r)[:300]}")
pid = r["prompt_id"]
deadline = time.time() + 180
while time.time() < deadline:
time.sleep(0.1)
h = requests.get(f"{COMFY}/history/{pid}").json()
if pid not in h:
continue
st = h[pid].get("status", {})
if st.get("status_str") == "error":
for m in st.get("messages", []):
if m[0] == "execution_error":
raise RuntimeError(str(m[1])[:300])
raise RuntimeError("execution error")
if "17" in h[pid].get("outputs", {}):
ts = {mm[0]: mm[1].get("timestamp") for mm in st["messages"]}
return (ts["execution_success"] - ts["execution_start"]) / 1000.0
raise TimeoutError("run exceeded 180s")
CONFIGS = [
("flux2.0/flux-2-klein-9b-fp8.safetensors", "fp8_e4m3fn", 6, "9B fp8 (当前)"),
("flux2.0/flux-2-klein-9b-fp8.safetensors", "fp8_e4m3fn_fast", 6, "9B fp8-fast"),
("flux2.0/flux-2-klein-9b-fp8.safetensors", "fp8_e4m3fn_fast", 4, "9B fp8-fast s4"),
("flux-2-klein-4b-fp8.safetensors", "fp8_e4m3fn", 6, "4B fp8"),
("flux-2-klein-4b-fp8.safetensors", "fp8_e4m3fn_fast", 6, "4B fp8-fast"),
("flux-2-klein-4b-fp8.safetensors", "fp8_e4m3fn_fast", 4, "4B fp8-fast s4"),
]
fname = prep_and_upload()
print("input uploaded:", fname)
print(f"{'配置':<22}{'warmup':>10}{'run1':>10}{'run2':>10}{'best':>10}")
for model, dtype, steps, label in CONFIGS:
times = []
for i in range(3): # 1 warmup + 2 measured
try:
t = run_once(fname, model, dtype, steps)
except Exception as e:
t = float('nan'); print("ERR", label, e)
times.append(t)
best = min(times[1:])
print(f"{label:<22}{times[0]:>9.2f}s{times[1]:>9.2f}s{times[2]:>9.2f}s{best:>9.2f}s")
+69
View File
@@ -0,0 +1,69 @@
#!/usr/bin/env python3
"""Steps sweep + resolution test on the working 9B fp8-fast config."""
import io, time
import requests
import numpy as np
from PIL import Image, ImageFilter
import app as A
COMFY = "http://127.0.0.1:8188"
MODEL = "flux2.0/flux-2-klein-9b-fp8.safetensors"
DTYPE = "fp8_e4m3fn_fast"
def upload(scale=1.0):
image = Image.open("用来重绘.jpg").convert("RGB")
mask_img = Image.open("用来重绘.png").convert("RGBA")
if scale != 1.0:
w, h = image.size
w, h = int(w * scale) // 8 * 8, int(h * scale) // 8 * 8
image = image.resize((w, h), Image.LANCZOS)
mask_data = np.max(np.array(mask_img), axis=2)
m = Image.fromarray(mask_data, mode="L")
if m.size != image.size:
m = m.resize(image.size, Image.LANCZOS)
m = m.filter(ImageFilter.GaussianBlur(radius=4))
alpha = Image.eval(m, lambda x: 255 - x)
r, g, b = image.split()
rgba = Image.merge("RGBA", (r, g, b, alpha))
buf = io.BytesIO(); rgba.save(buf, format="PNG"); buf.seek(0)
up = requests.post(f"{COMFY}/upload/image",
files={"image": ("hair_input.png", buf, "image/png")}).json()
return up["name"], image.size
def run(fname, steps):
wf = A.build_workflow(fname, "填充遮罩区域的头发")
wf["16"]["inputs"]["unet_name"] = MODEL
wf["16"]["inputs"]["weight_dtype"] = DTYPE
wf["1"]["inputs"]["steps"] = steps
pid = requests.post(f"{COMFY}/prompt", json={"prompt": wf}).json()["prompt_id"]
dl = time.time() + 120
while time.time() < dl:
time.sleep(0.1)
h = requests.get(f"{COMFY}/history/{pid}").json()
if pid in h and "17" in h[pid].get("outputs", {}):
ts = {m[0]: m[1].get("timestamp") for m in h[pid]["status"]["messages"]}
return (ts["execution_success"] - ts["execution_start"]) / 1000.0
return float("nan")
print("=== 步数扫描 (9B fp8-fast, 原分辨率 1024x775) ===", flush=True)
fname, sz = upload(1.0)
run(fname, 6) # warmup
res = {}
for s in [2, 3, 4, 6, 8]:
t = min(run(fname, s), run(fname, s))
res[s] = t
print(f" steps={s}: {t:.2f}s", flush=True)
# derive per-step cost & fixed overhead via two points
per = (res[8] - res[2]) / 6
fixed = res[2] - per * 2
print(f" -> 每步 ~{per:.3f}s, 固定开销(VAE/编码/colormatch/加载) ~{fixed:.2f}s", flush=True)
print("\n=== 分辨率影响 (steps=4) ===", flush=True)
for scale in [1.0, 0.75, 0.6]:
fn, s2 = upload(scale)
run(fn, 4) # warmup
t = min(run(fn, 4), run(fn, 4))
print(f" {s2[0]}x{s2[1]} ({s2[0]*s2[1]/1e6:.2f}MP): {t:.2f}s", flush=True)
+69
View File
@@ -0,0 +1,69 @@
#!/usr/bin/env python3
"""Generate result images at different step counts for quality comparison."""
import io, time
import requests
import numpy as np
from PIL import Image, ImageFilter
import app as A
COMFY = "http://127.0.0.1:8188"
MODEL = "flux2.0/flux-2-klein-9b-fp8.safetensors"
DTYPE = "fp8_e4m3fn_fast"
OUT = "output"
image = Image.open("用来重绘.jpg").convert("RGB")
mask_img = Image.open("用来重绘.png").convert("RGBA")
mask_data = np.max(np.array(mask_img), axis=2)
m = Image.fromarray(mask_data, mode="L")
if m.size != image.size:
m = m.resize(image.size, Image.LANCZOS)
m = m.filter(ImageFilter.GaussianBlur(radius=4))
alpha = Image.eval(m, lambda x: 255 - x)
r, g, b = image.split()
rgba = Image.merge("RGBA", (r, g, b, alpha))
buf = io.BytesIO(); rgba.save(buf, format="PNG"); buf.seek(0)
fname = requests.post(f"{COMFY}/upload/image",
files={"image": ("hair_input.png", buf, "image/png")}).json()["name"]
# fixed seed for fair comparison
SEED = 123456789
imgs = []
labels = []
for steps in [2, 3, 4, 6]:
wf = A.build_workflow(fname, "填充遮罩区域的头发", seed=SEED)
wf["16"]["inputs"]["unet_name"] = MODEL
wf["16"]["inputs"]["weight_dtype"] = DTYPE
wf["1"]["inputs"]["steps"] = steps
pid = requests.post(f"{COMFY}/prompt", json={"prompt": wf}).json()["prompt_id"]
t0 = time.time()
while True:
time.sleep(0.1)
h = requests.get(f"{COMFY}/history/{pid}").json()
if pid in h and "17" in h[pid].get("outputs", {}):
ts = {mm[0]: mm[1].get("timestamp") for mm in h[pid]["status"]["messages"]}
dur = (ts["execution_success"] - ts["execution_start"]) / 1000.0
info = h[pid]["outputs"]["17"]["images"][0]
data = requests.get(f"{COMFY}/view", params={
"filename": info["filename"], "subfolder": info.get("subfolder", ""),
"type": info.get("type", "output")}).content
im = Image.open(io.BytesIO(data)).convert("RGB")
imgs.append(im)
labels.append(f"steps={steps} {dur:.2f}s")
print(f"steps={steps}: {dur:.2f}s", flush=True)
break
# build side-by-side contact sheet
from PIL import ImageDraw
h0 = imgs[0].height
w0 = imgs[0].width
pad = 10
bar = 28
sheet = Image.new("RGB", (w0 * len(imgs) + pad * (len(imgs) + 1),
h0 + bar + pad * 2), (26, 26, 46))
d = ImageDraw.Draw(sheet)
for i, (im, lb) in enumerate(zip(imgs, labels)):
x = pad + i * (w0 + pad)
sheet.paste(im, (x, bar + pad))
d.text((x + 4, 6), lb, fill=(233, 69, 96))
sheet.save(f"{OUT}/compare_steps.png")
print("saved:", f"{OUT}/compare_steps.png", flush=True)
+192
View File
@@ -0,0 +1,192 @@
<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>发型补全工具</title>
<style>
* { margin: 0; padding: 0; box-sizing: border-box; }
body { font-family: -apple-system, sans-serif; background: #1a1a2e; color: #eee; min-height: 100vh; padding: 20px; }
h1 { text-align: center; margin-bottom: 20px; color: #e94560; font-size: 28px; }
.container { max-width: 1400px; margin: 0 auto; display: grid; grid-template-columns: 1fr 1fr; gap: 24px; }
.panel { background: #16213e; border-radius: 12px; padding: 20px; }
.panel h2 { margin-bottom: 16px; font-size: 18px; color: #e94560; }
.controls { display: flex; flex-wrap: wrap; gap: 12px; margin-bottom: 16px; align-items: center; }
.controls label { font-size: 14px; color: #aaa; }
input[type="file"] { color: #ddd; }
input[type="text"] { flex: 1; min-width: 200px; padding: 8px 12px; border-radius: 6px; border: 1px solid #444; background: #0f3460; color: #eee; font-size: 14px; }
button { padding: 10px 24px; border: none; border-radius: 6px; cursor: pointer; font-size: 14px; font-weight: 600; transition: all 0.2s; }
.btn-upload { background: #0f3460; color: #eee; border: 1px solid #e94560; }
.btn-upload:hover { background: #1a4a7a; }
.btn-generate { background: #e94560; color: #fff; font-size: 16px; padding: 12px 36px; }
.btn-generate:hover { background: #c73650; }
.btn-generate:disabled { background: #555; cursor: not-allowed; }
.image-wrapper { display: flex; gap: 12px; flex-wrap: wrap; border: 2px dashed #444; border-radius: 8px; padding: 12px; min-height: 300px; background: #0f3460; }
.image-item { flex: 1; min-width: 200px; }
.image-item img { max-width: 100%; border-radius: 6px; }
.image-item h4 { font-size: 12px; color: #aaa; margin-bottom: 6px; }
.placeholder { color: #666; font-size: 16px; text-align: center; padding: 60px 20px; width: 100%; }
.result-area { display: flex; gap: 16px; flex-wrap: wrap; }
.result-area img { max-width: 100%; border-radius: 8px; }
.result-item { flex: 1; min-width: 250px; }
.result-item h3 { font-size: 14px; color: #aaa; margin-bottom: 8px; text-align: center; }
.loading { text-align: center; padding: 40px; color: #e94560; font-size: 18px; }
.loading .spinner { display: inline-block; width: 40px; height: 40px; border: 4px solid #333; border-top-color: #e94560; border-radius: 50%; animation: spin 1s linear infinite; margin-bottom: 12px; }
@keyframes spin { to { transform: rotate(360deg); } }
.error { color: #ff6b6b; padding: 16px; background: #2a1a1a; border-radius: 8px; margin-top: 12px; }
</style>
</head>
<body>
<h1>💇 发型补全工具</h1>
<div class="container">
<!-- Left: Input -->
<div class="panel">
<h2>1. 上传图片 & 遮罩</h2>
<div class="controls">
<label>人物图片:</label>
<input type="file" id="imageInput" accept="image/*" class="btn-upload">
</div>
<div class="controls">
<label>遮罩图片:</label>
<input type="file" id="maskInput" accept="image/*" class="btn-upload">
</div>
<div class="image-wrapper" id="imageWrapper">
<div class="placeholder" id="placeholder">请上传人物图片和遮罩图片</div>
</div>
<div class="controls" style="margin-top:16px">
<label>提示词:</label>
<input type="text" id="promptInput" value="填充遮罩区域的头发">
</div>
<div style="text-align:center; margin-top:16px">
<button class="btn-generate" id="generateBtn" disabled>🚀 生成</button>
</div>
</div>
<!-- Right: Result -->
<div class="panel">
<h2>2. 对比结果</h2>
<div id="resultArea">
<div class="placeholder">生成结果将显示在这里</div>
</div>
</div>
</div>
<script>
const imageInput = document.getElementById('imageInput');
const maskInput = document.getElementById('maskInput');
const imageWrapper = document.getElementById('imageWrapper');
const placeholder = document.getElementById('placeholder');
const promptInput = document.getElementById('promptInput');
const generateBtn = document.getElementById('generateBtn');
const resultArea = document.getElementById('resultArea');
let originalImage = null;
let maskImage = null;
imageInput.addEventListener('change', (e) => {
const file = e.target.files[0];
if (!file) return;
const reader = new FileReader();
reader.onload = (ev) => {
const img = new Image();
img.onload = () => {
originalImage = { img: img, file: file };
updatePreview();
checkReady();
};
img.src = ev.target.result;
};
reader.readAsDataURL(file);
});
maskInput.addEventListener('change', (e) => {
const file = e.target.files[0];
if (!file) return;
const reader = new FileReader();
reader.onload = (ev) => {
const img = new Image();
img.onload = () => {
maskImage = { img: img, file: file };
updatePreview();
checkReady();
};
img.src = ev.target.result;
};
reader.readAsDataURL(file);
});
function updatePreview() {
placeholder.style.display = 'none';
let html = '';
if (originalImage) {
html += `<div class="image-item"><h4>人物图片</h4><img src="${originalImage.img.src}" alt="原图"></div>`;
}
if (maskImage) {
html += `<div class="image-item"><h4>遮罩图片</h4><img src="${maskImage.img.src}" alt="遮罩"></div>`;
}
imageWrapper.innerHTML = html;
}
function checkReady() {
generateBtn.disabled = !(originalImage && maskImage);
}
generateBtn.addEventListener('click', async () => {
if (!originalImage || !maskImage) return;
generateBtn.disabled = true;
generateBtn.textContent = '⏳ 生成中...';
const startTime = performance.now();
resultArea.innerHTML = '<div class="loading"><div class="spinner"></div><br>正在调用 ComfyUI 生成,请耐心等待...<div id="liveTimer" style="margin-top:8px;font-size:15px;color:#aaa">已用时 0.0s</div></div>';
const liveTimer = document.getElementById('liveTimer');
const timerId = setInterval(() => {
if (liveTimer) liveTimer.textContent = '已用时 ' + ((performance.now() - startTime) / 1000).toFixed(1) + 's';
}, 100);
try {
const formData = new FormData();
formData.append('image', originalImage.file, 'original.' + originalImage.file.name.split('.').pop());
formData.append('mask', maskImage.file, 'mask.' + maskImage.file.name.split('.').pop());
formData.append('prompt', promptInput.value);
const resp = await fetch('/api/generate', { method: 'POST', body: formData });
if (!resp.ok) {
const err = await resp.json();
throw new Error(err.error || 'Generation failed');
}
const resultBlob = await resp.blob();
const resultUrl = URL.createObjectURL(resultBlob);
const elapsed = ((performance.now() - startTime) / 1000).toFixed(1);
// 服务端纯推理耗时(若返回该响应头)
const serverTime = resp.headers.get('X-Generate-Time');
const serverInfo = serverTime ? `,服务端推理 ${parseFloat(serverTime).toFixed(1)}s` : '';
resultArea.innerHTML = `
<div style="text-align:center;margin-bottom:12px;color:#4ade80;font-size:16px;font-weight:600">
⏱️ 本次重绘耗时 ${elapsed}s${serverInfo}
</div>
<div class="result-area">
<div class="result-item">
<h3>原图</h3>
<img src="${originalImage.img.src}" alt="原图">
</div>
<div class="result-item">
<h3>生成结果</h3>
<img src="${resultUrl}" alt="生成结果">
</div>
</div>
`;
} catch (err) {
const elapsed = ((performance.now() - startTime) / 1000).toFixed(1);
resultArea.innerHTML = `<div class="error">❌ ${err.message}<br><span style="color:#aaa;font-size:13px">(耗时 ${elapsed}s</span></div>`;
} finally {
clearInterval(timerId);
generateBtn.disabled = false;
generateBtn.textContent = '🚀 生成';
}
});
</script>
</body>
</html>
Binary file not shown.

After

Width:  |  Height:  |  Size: 1.2 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 3.3 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 899 KiB

+52
View File
@@ -0,0 +1,52 @@
#!/bin/bash
# 启动发型补全服务
cd "$(dirname "$0")"
PID_FILE="hair_service.pid"
LOG_FILE="hair_service.log"
# 检查是否已在运行
if [ -f "$PID_FILE" ]; then
PID=$(cat "$PID_FILE")
if kill -0 "$PID" 2>/dev/null; then
echo "服务已在运行 (PID: $PID)"
exit 0
else
echo "清理无效的 PID 文件..."
rm "$PID_FILE"
fi
fi
# 检查 ComfyUI 是否运行
if ! curl -s -o /dev/null -w "%{http_code}" http://127.0.0.1:8188/ >/dev/null 2>&1; then
echo "警告: ComfyUI 未运行 (http://127.0.0.1:8188)"
echo "请先启动 ComfyUI: python /home/ubuntu/ComfyUI/main.py --listen"
fi
# 启动服务
echo "启动发型补全服务..."
/home/ubuntu/ComfyUI/venv/bin/python app.py >> "$LOG_FILE" 2>&1 &
PID=$!
echo "$PID" > "$PID_FILE"
# 等待启动
sleep 2
if curl -s -o /dev/null -w "%{http_code}" http://127.0.0.1:8899/ | grep -q "200"; then
echo "服务启动成功!"
echo "本机: http://127.0.0.1:8899"
# 打印局域网 IP,方便其他机器访问(app.py 已绑定 0.0.0.0
LAN_IPS=$(hostname -I 2>/dev/null | tr ' ' '\n' | grep -v '^$' || true)
if [ -n "$LAN_IPS" ]; then
echo "外网/局域网访问:"
for ip in $LAN_IPS; do
echo " http://${ip}:8899"
done
fi
echo "PID: $PID"
echo "日志: $LOG_FILE"
else
echo "服务启动失败,请检查日志: $LOG_FILE"
rm "$PID_FILE"
exit 1
fi
+37
View File
@@ -0,0 +1,37 @@
#!/bin/bash
# 停止发型补全服务
cd "$(dirname "$0")"
PID_FILE="hair_service.pid"
if [ ! -f "$PID_FILE" ]; then
echo "服务未运行"
exit 0
fi
PID=$(cat "$PID_FILE")
if kill -0 "$PID" 2>/dev/null; then
echo "正在停止服务 (PID: $PID)..."
kill "$PID"
# 等待进程退出
for i in {1..10}; do
if ! kill -0 "$PID" 2>/dev/null; then
echo "服务已停止"
rm "$PID_FILE"
exit 0
fi
sleep 1
done
# 强制终止
echo "强制终止进程..."
kill -9 "$PID"
rm "$PID_FILE"
echo "服务已停止"
else
echo "进程已不存在,清理 PID 文件..."
rm "$PID_FILE"
fi
+42
View File
@@ -0,0 +1,42 @@
#!/usr/bin/env python3
"""Test script: send image+mask to the local service and save result."""
import requests
import sys
import os
SERVICE_URL = "http://127.0.0.1:8899"
IMAGE_PATH = "/home/ubuntu/hair/local_test/用来重绘.jpg"
MASK_PATH = "/home/ubuntu/hair/local_test/用来重绘.png"
OUTPUT_DIR = "/home/ubuntu/hair/local_test/output"
os.makedirs(OUTPUT_DIR, exist_ok=True)
print(f"Sending image: {IMAGE_PATH}")
print(f"Sending mask: {MASK_PATH}")
with open(IMAGE_PATH, "rb") as f:
img_data = f.read()
with open(MASK_PATH, "rb") as f:
mask_data = f.read()
resp = requests.post(
f"{SERVICE_URL}/api/generate",
files={
"image": ("original.jpg", img_data, "image/jpeg"),
"mask": ("mask.png", mask_data, "image/png"),
},
data={"prompt": "填充遮罩区域的头发"},
timeout=600,
)
print(f"Status: {resp.status_code}")
print(f"Content-Type: {resp.headers.get('Content-Type')}")
if resp.status_code == 200 and "image" in resp.headers.get("Content-Type", ""):
out_path = os.path.join(OUTPUT_DIR, "result.png")
with open(out_path, "wb") as f:
f.write(resp.content)
print(f"SUCCESS! Result saved to: {out_path}")
else:
print(f"FAILED! Response: {resp.text[:2000]}")
sys.exit(1)
Binary file not shown.

After

Width:  |  Height:  |  Size: 81 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 8.7 KiB

+126
View File
@@ -0,0 +1,126 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""重新生成 bench3/4/5/7 报告,在最左边加原图列。"""
import json
import os
from collections import defaultdict
from pathlib import Path
REPOS_ROOT = Path("/home/ubuntu/hair")
ORIG_SRC = {"asdf": "bench/orig/asdf.jpg", "qwer": "bench/orig/qwer.jpg",
"girl2": "bench/orig/girl2.jpg", "girl5": "bench/orig/girl5.jpg"}
# bench编号 -> (输出目录, 部署HTML名, 报告标题后缀)
BENCHES = [
(3, "美颜(磨皮+美颜)"),
(4, "磨皮"),
(5, "美白"),
(7, "纯生发"),
]
def img_src(path, bench_num):
if not path or not os.path.isfile(path):
return None
return f"bench{bench_num}/" + os.path.basename(path)
def gen_report(bench_num, title_suffix):
bench_dir = REPOS_ROOT / f"benchmark_out/bench{bench_num}"
results = bench_dir / "results.json"
if not results.exists():
print(f" 跳过 bench{bench_num}: results.json 不存在")
return
d = json.load(open(results, encoding="utf-8"))
titles = d["res_titles"]
rows = d["rows"]
prompt = d.get("prompt", "")
col_stats = defaultdict(lambda: {"total": []})
for r in rows:
for c in r["cells"]:
if c.get("ok"):
col_stats[c["res_title"]]["total"].append(c["total_ms"])
# 表头:原图列 + 分辨率列
headers = ['<th class="col-label">原图</th>']
for t in titles:
s = col_stats.get(t)
avg = sum(s["total"]) // len(s["total"]) if s and s["total"] else 0
headers.append(f'<th class="col-label"><div class="col-title">{t}</div>'
f'<div class="col-stat">均{avg/1000:.1f}s</div></th>')
body_rows = []
for r in rows:
orig_src = ORIG_SRC.get(r["img"])
label = f'<div class="row-label">{r["img"]}<br><b>{r["hair_name"]}</b></div>'
# 原图列:显示输入原图
orig_cell = (f'<td class="cell-orig"><div class="row-label-cell">{label}</div>'
f'<img class="orig-img" src="{orig_src}"></td>')
cells = [orig_cell]
for c in r["cells"]:
src = img_src(c.get("grown_path"), bench_num) if c.get("ok") else None
if src:
t = c.get("total_ms", 0)
cells.append(f'<td class="cell-result"><img class="result-img" src="{src}" loading="lazy">'
f'<div class="cell-time">{t/1000:.1f}s</div></td>')
else:
cells.append(f'<td class="cell-result"><div class="na">⚠</div></td>')
body_rows.append(f'<tr>{"".join(cells)}</tr>')
html = f"""<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>重绘分辨率对比({title_suffix})</title>
<style>
* {{ box-sizing: border-box; margin: 0; padding: 0; }}
body {{ font-family: -apple-system, sans-serif; background: #f5f5f5; padding: 16px; }}
h1 {{ font-size: 20px; margin-bottom: 4px; }}
.subtitle {{ color: #888; font-size: 12px; margin-bottom: 12px; }}
.legend {{ background: #fff; border-radius: 8px; padding: 10px 16px; margin-bottom: 12px; font-size: 12px; color: #555; }}
.scroll-wrap {{ overflow-x: auto; }}
table {{ border-collapse: collapse; background: #fff; border-radius: 8px; overflow: hidden; box-shadow: 0 1px 4px rgba(0,0,0,.06); }}
th, td {{ border: 1px solid #eee; padding: 6px; vertical-align: top; text-align: center; }}
th {{ background: #f9fafb; position: sticky; top: 0; }}
.col-label {{ min-width: 130px; max-width: 150px; }}
.col-title {{ font-size: 12px; font-weight: 700; color: #374151; }}
.col-stat {{ font-size: 10px; color: #9ca3af; margin-top: 2px; }}
.row-label {{ font-size: 11px; color: #6b7280; }}
.row-label b {{ color: #1f2937; }}
.row-label-cell {{ font-size: 11px; color: #6b7280; margin-bottom: 4px; }}
.row-label-cell b {{ color: #1f2937; font-size: 13px; }}
img {{ border-radius: 4px; max-width: 130px; max-height: 160px; object-fit: contain; background: #f3f4f6; }}
.orig-img {{ border: 2px solid #d1d5db; }}
.cell-time {{ font-size: 10px; color: #9ca3af; margin-top: 2px; }}
.na {{ color: #d1d5db; font-size: 12px; padding: 40px 10px; }}
</style>
</head>
<body>
<h1>📊 重绘分辨率对比提示词{title_suffix}</h1>
<p class="subtitle">4×5发型=20 · 每行原图+4分辨率 · steps=15 · 提示词="{prompt}" · 80/80成功 · 0 OOM</p>
<div class="legend">最左列为输入原图列标题下为平均总耗时横向滚动查看</div>
<div class="scroll-wrap">
<table>
<tr>{"".join(headers)}</tr>
{"".join(body_rows)}
</table>
</div>
</body>
</html>"""
deploy = REPOS_ROOT / "static" / f"bench{bench_num}_report.html"
deploy.write_text(html, encoding="utf-8")
print(f" ✓ bench{bench_num} ({title_suffix}): {deploy.name}")
def main():
print("重新生成报告(加原图列):")
for num, suffix in BENCHES:
gen_report(num, suffix)
print("完成")
if __name__ == "__main__":
main()
-156
View File
@@ -1,156 +0,0 @@
"""批量调用接口12/api/v1/hairline/grow_v2)生成对比素材。
20 张女生照片 × 5 种发际线发型仅非高清= 100 张输出
并发 2失败的跳过并记录原因结果图落盘到 static/report_hairline_v2/img/
元数据落盘 static/report_hairline_v2/results.json供生成报告用
用法 python scripts/batch_grow_v2.py
"""
import base64
import json
import os
import time
from concurrent.futures import ThreadPoolExecutor, as_completed
import httpx
API = "http://127.0.0.1:8187/api/v1/hairline/grow_v2"
TOKEN = "dev-shared-secret-2026"
CONCURRENCY = 2
INPUT_DIR = "/home/xsl/hair/image/test"
OUT_DIR = "/home/xsl/hair/static/report_hairline_v2"
IMG_DIR = os.path.join(OUT_DIR, "img")
ORIG_DIR = os.path.join(OUT_DIR, "orig")
# 5 种发际线发型(= change_hair hair_id
HAIRSTYLES = [
("chang_zhixian", "直线"),
("chang_tuoyuan", "椭圆"),
("chang_bolang", "波浪"),
("chang_xinxing", "心形"),
("chang_huaban", "花瓣"),
]
HR_OPTIONS = [(False, "nohr")] # 仅非高清
def list_inputs():
files = sorted(f for f in os.listdir(INPUT_DIR) if f.lower().endswith((".jpg", ".png")))
return files
def one_call(stem, face_file, hair_id, hair_cn, is_hr, hr_tag):
"""调用一次接口,落盘结果图。返回结果 dict。"""
src = os.path.join(INPUT_DIR, face_file)
out_name = f"{stem}__{hair_id}__{hr_tag}.jpg"
out_path = os.path.join(IMG_DIR, out_name)
# 断点续跑:已存在的图直接跳过,不重复调用
if os.path.exists(out_path) and os.path.getsize(out_path) > 1024:
return {
"stem": stem, "face_file": face_file, "hair_id": hair_id, "hair_cn": hair_cn,
"is_hr": is_hr, "hr_tag": hr_tag, "ok": True,
"out": f"img/{out_name}", "size": None,
"ms": 0, "error": None, "skipped": True,
}
t0 = time.time()
try:
with open(src, "rb") as fh:
files = {"image_file": (face_file, fh.read(), "image/jpeg")}
data = {"hairline_id": hair_id, "is_hr": str(is_hr).lower()}
with httpx.Client(timeout=180.0) as c:
resp = c.post(API, headers={"X-Internal-Token": TOKEN}, files=files, data=data)
j = resp.json()
if j.get("code") != 0 or not j.get("data"):
raise RuntimeError(f"code={j.get('code')} msg={j.get('message')}")
b64 = j["data"]["final_base64"].split(",", 1)[1]
raw = base64.b64decode(b64)
with open(out_path, "wb") as fh:
fh.write(raw)
return {
"stem": stem, "face_file": face_file, "hair_id": hair_id, "hair_cn": hair_cn,
"is_hr": is_hr, "hr_tag": hr_tag, "ok": True,
"out": f"img/{out_name}", "size": j["data"].get("image_size"),
"ms": int((time.time() - t0) * 1000), "error": None,
}
except Exception as ex: # noqa: BLE001
return {
"stem": stem, "face_file": face_file, "hair_id": hair_id, "hair_cn": hair_cn,
"is_hr": is_hr, "hr_tag": hr_tag, "ok": False,
"out": None, "size": None, "ms": int((time.time() - t0) * 1000),
"error": str(ex)[:200],
}
def main():
os.makedirs(IMG_DIR, exist_ok=True)
os.makedirs(ORIG_DIR, exist_ok=True)
faces = list_inputs()
print(f"输入 {len(faces)} 张脸 × {len(HAIRSTYLES)} 发型 × {len(HR_OPTIONS)} = "
f"{len(faces)*len(HAIRSTYLES)*len(HR_OPTIONS)} 次调用,并发 {CONCURRENCY}")
# 1. 先把原图拷一份到 orig/(报告要用)
import shutil
for f in faces:
stem = os.path.splitext(f)[0]
dst = os.path.join(ORIG_DIR, f"{stem}.jpg")
if not os.path.exists(dst):
shutil.copy2(os.path.join(INPUT_DIR, f), dst)
# 2. 构造全部任务
tasks = []
for f in faces:
stem = os.path.splitext(f)[0]
for hair_id, hair_cn in HAIRSTYLES:
for is_hr, hr_tag in HR_OPTIONS:
tasks.append((stem, f, hair_id, hair_cn, is_hr, hr_tag))
results = []
done = 0
total = len(tasks)
t_start = time.time()
with ThreadPoolExecutor(max_workers=CONCURRENCY) as ex:
futs = {ex.submit(one_call, *t): t for t in tasks}
for fut in as_completed(futs):
r = fut.result()
results.append(r)
done += 1
status = "OK " if r["ok"] else "FAIL"
if r.get("skipped"):
print(f"[{done}/{total}] SKIP {r['stem']} {r['hair_cn']} {r['hr_tag']}")
elif r["ok"]:
print(f"[{done}/{total}] {status} {r['stem']} {r['hair_cn']} {r['hr_tag']} "
f"({r['ms']}ms)", flush=True)
else:
print(f"[{done}/{total}] {status} {r['stem']} {r['hair_cn']} {r['hr_tag']} "
f"-> {r['error']}")
elapsed = time.time() - t_start
ok = sum(1 for r in results if r["ok"])
fail = len(results) - ok
# 按稳定顺序排序,报告好看
order = {s: i for i, s in enumerate(HAIRSTYLES)}
hr_order = {True: 0, False: 1}
face_order = {os.path.splitext(f)[0]: i for i, f in enumerate(faces)}
results.sort(key=lambda r: (face_order.get(r["stem"], 0),
order.get((r["hair_id"], r["hair_cn"]), 0),
hr_order.get(r["is_hr"], 0)))
meta = {
"total": total, "ok": ok, "fail": fail,
"elapsed_sec": round(elapsed, 1), "concurrency": CONCURRENCY,
"hairstyles": [{"id": h, "cn": c} for h, c in HAIRSTYLES],
"hr_options": [{"is_hr": is_hr, "tag": tag} for is_hr, tag in HR_OPTIONS],
"faces": [os.path.splitext(f)[0] for f in faces],
"generated_at": time.strftime("%Y-%m-%d %H:%M:%S"),
}
out = {"meta": meta, "results": results}
with open(os.path.join(OUT_DIR, "results.json"), "w", encoding="utf-8") as fh:
json.dump(out, fh, ensure_ascii=False, indent=2)
print(f"\n完成:{ok}/{total} 成功,{fail} 失败,耗时 {elapsed:.1f}s")
print(f"结果图 -> {IMG_DIR}")
print(f"元数据 -> {OUT_DIR}/results.json")
if __name__ == "__main__":
main()
-220
View File
@@ -1,220 +0,0 @@
"""根据 results.json 生成发际线生发对比报告 HTML。
报告布局原图 vs 结果对比
- 顶部总览统计成功/失败数耗时参数
- 按脸分组每张脸一个区块
- 原图
- 5 发型 × {高清, 非高清} 网格 10 失败的格子标注原因
- 失败用例汇总表
输出static/report_hairline_v2/index.html
"""
import html
import json
import os
from urllib.parse import quote
OUT_DIR = "/home/xsl/hair/static/report_hairline_v2"
RESULTS = os.path.join(OUT_DIR, "results.json")
TARGET = os.path.join(OUT_DIR, "index.html")
def url(path):
"""把相对路径里的中文做 URL 编码,分隔符 '/' 保留。
Starlette StaticFiles 对未编码中文路径返回 400编码后所有浏览器稳定可加载
"""
return "/".join(quote(seg) for seg in path.split("/"))
def main():
with open(RESULTS, encoding="utf-8") as fh:
data = json.load(fh)
meta = data["meta"]
results = data["results"]
hairstyles = meta["hairstyles"] # [{id, cn}]
faces = meta["faces"] # [stem, ...]
hr_opts = meta["hr_options"] # [{is_hr, tag}]
# 索引:(stem, hair_id, hr_tag) -> result
idx = {}
for r in results:
idx[(r["stem"], r["hair_id"], r["hr_tag"])] = r
# 统计
ok = sum(1 for r in results if r["ok"])
fail = len(results) - ok
parts = []
parts.append(f"""<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>发际线生发对比报告 · 接口12 grow_v2</title>
<style>
:root {{
--bg:#0f1115; --card:#1a1d24; --border:#2a2f3a; --txt:#e6e6e6;
--muted:#8a93a3; --accent:#6ea8fe; --ok:#4ade80; --fail:#f87171;
}}
* {{ box-sizing:border-box; }}
body {{ margin:0; background:var(--bg); color:var(--txt);
font-family:-apple-system,"Segoe UI","PingFang SC","Microsoft YaHei",sans-serif;
line-height:1.5; }}
header {{ padding:24px 32px; border-bottom:1px solid var(--border); }}
header h1 {{ margin:0 0 8px; font-size:22px; }}
header .sub {{ color:var(--muted); font-size:14px; }}
.stats {{ display:flex; gap:16px; flex-wrap:wrap; margin-top:16px; }}
.stat {{ background:var(--card); border:1px solid var(--border); border-radius:8px;
padding:12px 16px; min-width:120px; }}
.stat .n {{ font-size:24px; font-weight:600; }}
.stat .l {{ font-size:12px; color:var(--muted); }}
.stat.ok .n {{ color:var(--ok); }}
.stat.fail .n {{ color:var(--fail); }}
main {{ padding:24px 32px; }}
.face-block {{ background:var(--card); border:1px solid var(--border);
border-radius:12px; padding:20px; margin-bottom:24px; }}
.face-head {{ display:flex; align-items:center; gap:12px; margin-bottom:16px; }}
.face-head h2 {{ margin:0; font-size:18px; }}
.face-head .orig-thumb {{ width:64px; height:64px; object-fit:cover;
border-radius:8px; border:1px solid var(--border); }}
.grid {{ display:grid; grid-template-columns:repeat({len(hairstyles)+1}, 1fr);
gap:10px; align-items:start; }}
.col-hdr {{ font-size:12px; color:var(--muted); text-align:center; padding:6px 4px;
border-bottom:1px solid var(--border); }}
.col-hdr.orig {{ color:var(--accent); }}
.cell {{ position:relative; }}
.cell img {{ width:100%; border-radius:6px; display:block;
border:1px solid var(--border); }}
.cell .cap {{ font-size:11px; color:var(--muted); margin-top:4px; text-align:center; }}
.cell.fail .failbox {{ aspect-ratio:3/4; background:#2a1518; border:1px solid #5c2a30;
border-radius:6px; display:flex; align-items:center;
justify-content:center; padding:8px; text-align:center;
font-size:11px; color:var(--fail); }}
.tag {{ display:inline-block; font-size:11px; padding:1px 6px; border-radius:4px;
background:#243044; color:var(--accent); margin-left:6px; }}
.tag.no {{ background:#3a3526; color:#e0c97a; }}
.legend {{ font-size:13px; color:var(--muted); margin-bottom:16px; }}
.fail-table {{ width:100%; border-collapse:collapse; font-size:13px; margin-top:8px; }}
.fail-table th, .fail-table td {{ border:1px solid var(--border); padding:6px 10px; text-align:left; }}
.fail-table th {{ background:#1f232c; color:var(--muted); }}
.anchor {{ display:block; height:0; overflow:hidden; }}
footer {{ padding:24px 32px; color:var(--muted); font-size:12px; border-top:1px solid var(--border); }}
/* 点击放大 */
img.zoomable {{ cursor:zoom-in; transition:opacity .12s; }}
img.zoomable:hover {{ opacity:.85; }}
#lightbox {{ position:fixed; inset:0; background:rgba(0,0,0,.92); display:none;
align-items:center; justify-content:center; z-index:9999; padding:24px;
cursor:zoom-out; }}
#lightbox.open {{ display:flex; }}
#lightbox img {{ max-width:100%; max-height:100%; object-fit:contain;
border-radius:8px; box-shadow:0 8px 40px rgba(0,0,0,.6); }}
#lightbox .lb-cap {{ position:absolute; bottom:16px; left:0; right:0; text-align:center;
color:var(--muted); font-size:13px; }}
</style>
</head>
<body>
<header>
<h1>发际线生发对比报告 <span class="tag">接口12 · grow_v2</span></h1>
<div class="sub">固定pushed 遮罩 + multiband 融合 · mb_levels=5 · erode_cm=0.6 · 非高清</div>
<div class="sub">生成时间{html.escape(meta['generated_at'])} · 并发 {meta['concurrency']} · 耗时 {meta['elapsed_sec']}s</div>
<div class="stats">
<div class="stat"><div class="n">{meta['total']}</div><div class="l">总调用</div></div>
<div class="stat ok"><div class="n">{ok}</div><div class="l">成功</div></div>
<div class="stat fail"><div class="n">{fail}</div><div class="l">失败</div></div>
<div class="stat"><div class="n">{len(faces)}</div><div class="l">人脸数</div></div>
<div class="stat"><div class="n">{len(hairstyles)}</div><div class="l">发型数</div></div>
</div>
</header>
<main>
""")
# 图例
parts.append('<div class="legend">每张脸:第一列为原图,其余 5 列为发际线生发结果(非高清)。点击任意图片可放大。</div>')
# 每张脸一个区块:原图 + 5 发型横向并排
for stem in faces:
orig_rel = f"orig/{stem}.jpg"
parts.append('<div class="face-block">')
parts.append(f' <div class="face-head"><h2>{html.escape(stem)}</h2></div>')
# 网格:第一列原图,其余 5 列发型结果
parts.append('<div class="grid">')
# 表头
parts.append('<div class="col-hdr orig">原图</div>')
for h in hairstyles:
parts.append(f'<div class="col-hdr">{html.escape(h["cn"])}<br><span style="opacity:.6">{html.escape(h["id"])}</span></div>')
# 第一列:原图大图(可点击放大)
parts.append(
f'<div class="cell"><img class="zoomable" src="{url(orig_rel)}" '
f'data-full="{url(orig_rel)}" loading="lazy" alt="原图 {html.escape(stem)}">'
f'<div class="cap">原图</div></div>')
# 5 发型结果(hr_opts 现在只有 nohr 一档,直接取)
hr_tag = hr_opts[0]["tag"] if hr_opts else "nohr"
for h in hairstyles:
r = idx.get((stem, h["id"], hr_tag))
if r and r["ok"]:
ms = r["ms"]
parts.append(
f'<div class="cell"><img class="zoomable" src="{url(r["out"])}" '
f'data-full="{url(r["out"])}" loading="lazy" '
f'alt="{html.escape(stem)} {html.escape(h["cn"])}">'
f'<div class="cap">{ms}ms</div></div>')
else:
err = (r or {}).get("error", "未执行")
parts.append(
f'<div class="cell fail"><div class="failbox">{html.escape(err)}</div></div>')
parts.append('</div>') # grid
parts.append('</div>') # face-block
# 失败汇总
fails = [r for r in results if not r["ok"]]
if fails:
parts.append('<div class="face-block">')
parts.append(f'<h2>失败用例({len(fails)}</h2>')
parts.append('<table class="fail-table"><thead><tr>'
'<th>人脸</th><th>发型</th><th>耗时(ms)</th><th>原因</th>'
'</tr></thead><tbody>')
for r in fails:
parts.append(
f'<tr><td>{html.escape(r["stem"])}</td>'
f'<td>{html.escape(r["hair_cn"])}</td>'
f'<td>{r["ms"]}</td>'
f'<td>{html.escape(r["error"] or "")}</td></tr>')
parts.append('</tbody></table></div>')
parts.append(f"""
<footer>
接口<code>POST /api/v1/hairline/grow_v2</code> · 固定 pushed 遮罩 + multiband 融合 ·
数据源 results.json · 点击任意图片可放大查看
</footer>
</main>
<div id="lightbox"><img><div class="lb-cap"></div></div>
<script>
(function(){{
var lb=document.getElementById('lightbox'),lbImg=lb.querySelector('img'),
lbCap=lb.querySelector('.lb-cap');
function open(src,cap){{
lbImg.src=src; lbCap.textContent=cap||''; lb.classList.add('open');
}}
function close(){{ lb.classList.remove('open'); lbImg.src=''; }}
document.addEventListener('click',function(e){{
var t=e.target.closest('img.zoomable');
if(t){{ open(t.dataset.full||t.src, t.alt||''); }}
else if(e.target===lb||e.target===lbImg){{ close(); }}
}});
document.addEventListener('keydown',function(e){{
if(e.key==='Escape') close();
}});
}})();
</script>
</body>
</html>""")
with open(TARGET, "w", encoding="utf-8") as fh:
fh.write("".join(parts))
print(f"报告已生成:{TARGET}")
print(f"成功 {ok}/{meta['total']},失败 {fail}")
if __name__ == "__main__":
main()
Binary file not shown.

After

Width:  |  Height:  |  Size: 235 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 211 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 296 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 334 KiB

Some files were not shown because too many files have changed in this diff Show More