28 Commits
Author SHA1 Message Date
xslandCursor fe0e74ece8 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 23:03:33 +08:00
xsl 52913c94fc fix: 删除 MeasureResult.__init__ 中重复的七眼厘米赋值块 2026-07-27 23:17:22 +08:00
xsl 13526cb5b8 feat: 接口1/5/6 发际线弃用逻辑(顶庭<0.7cm)
发际线离头顶<0.7cm时判定分割不可靠,弃用发际线:
顶/上庭字段置null、face_total只算中下庭、标注图保留头顶线去掉发际线、
只标中/下庭。eye1/7竖向范围改用眉心。
2026-07-27 23:10:54 +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
50 changed files with 2800 additions and 544 deletions
+4
View File
@@ -49,3 +49,7 @@ 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
+327
View File
@@ -0,0 +1,327 @@
{
"16": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "flux-2-klein-4b-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_4b.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,皮肤加一点磨皮,再加一点美颜"
}
},
"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",
@@ -170,8 +170,8 @@
},
"16": {
"inputs": {
"unet_name": "flux2.0/flux-2-klein-9b-fp8.safetensors",
"weight_dtype": "fp8_e4m3fn"
"unet_name": "flux-2-klein-4b-fp8.safetensors",
"weight_dtype": "fp8_e4m3fn_fast"
},
"class_type": "UNETLoader",
"_meta": {
@@ -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,皮肤加一点磨皮,再加一点美颜"
},
"class_type": "JjkText",
"_meta": {
@@ -419,9 +419,9 @@
},
"61": {
"inputs": {
"clip_name": "qwen_3_8b_fp8mixed.safetensors",
"clip_name": "qwen_3_4b.safetensors",
"type": "flux2",
"device": "default"
"device": "cpu"
},
"class_type": "CLIPLoader",
"_meta": {
+128 -131
View File
@@ -138,7 +138,47 @@ app = FastAPI(
app.mount("/static", StaticFiles(directory="static"), name="static")
# 不校验鉴权的路径前缀(供网关探测 / 文档 / 静态)
_AUTH_EXEMPT = ("/health", "/docs", "/openapi.json", "/redoc", "/static", "/api/v1/debug")
_AUTH_EXEMPT = ("/health", "/docs", "/openapi.json", "/redoc", "/static",
"/api/v1/debug", "/api/v1/redraw",
"/api/swapHair", "/hairColor")
# ---------------------------------------------------------------------------
# change_hair 代理路由(解决 CORS 问题)
# ---------------------------------------------------------------------------
_CHANGE_HAIR_BASE = "http://127.0.0.1:8801"
@app.post("/api/swapHair/v1", tags=["change_hair"])
async def proxy_swap_hair(request: Request):
"""代理转发到 change_hair /api/swapHair/v1(换发型)"""
try:
import httpx
body = await request.body()
async with httpx.AsyncClient(timeout=300.0) as client:
resp = await client.post(f"{_CHANGE_HAIR_BASE}/api/swapHair/v1",
content=body,
headers={"Content-Type": "application/json"})
return JSONResponse(content=resp.json(), status_code=resp.status_code)
except Exception as e:
logger.exception("代理 swapHair 失败")
return err(1007, f"换发型服务异常:{e}")
@app.post("/hairColor/v2", tags=["change_hair"])
async def proxy_hair_color(request: Request):
"""代理转发到 change_hair /hairColor/v2(换发色)"""
try:
import httpx
body = await request.body()
async with httpx.AsyncClient(timeout=300.0) as client:
resp = await client.post(f"{_CHANGE_HAIR_BASE}/hairColor/v2",
content=body,
headers={"Content-Type": "application/json"})
return JSONResponse(content=resp.json(), status_code=resp.status_code)
except Exception as e:
logger.exception("代理 hairColor 失败")
return err(1007, f"换发色服务异常:{e}")
@app.middleware("http")
@@ -361,20 +401,36 @@ def _run_face_measure_data(image, variant="v1"):
logger.warning("头发/耳朵分割失败,回退方案A%s", seg_e)
result = measure_face(landmarks, hair_mask, w, h, head_pose=head_pose)
discarded = result.hairline_discarded
data = result.to_response()
vd = result.vertical
if variant == "v6":
vd = result.vertical
base_px = vd["upper_court_px"] + vd["middle_court_px"] + vd["lower_court_px"]
# 接口6 是三庭:去掉顶庭相关字段(top_court_cm / ratios.top_court / landmarks.hair_top
data["four_courts"]["ratios"] = {
"upper_court": round(vd["upper_court_px"] / base_px, 3),
"middle_court": round(vd["middle_court_px"] / base_px, 3),
"lower_court": round(vd["lower_court_px"] / base_px, 3),
}
data["four_courts"].pop("top_court_cm", None)
data["face_total_height_cm"] = round(
result.upper_cm + result.middle_cm + result.lower_cm, 2)
data["landmarks"].pop("hair_top", None)
if discarded:
# 发际线弃用:接口6 的上庭也依赖发际线,一并置 null;只保留中/下庭。
base_px = vd["middle_court_px"] + vd["lower_court_px"]
data["four_courts"]["upper_court_cm"] = None
data["four_courts"]["ratios"] = {
"upper_court": None,
"middle_court": round(vd["middle_court_px"] / base_px, 3),
"lower_court": round(vd["lower_court_px"] / base_px, 3),
}
data["four_courts"].pop("top_court_cm", None)
data["face_total_height_cm"] = round(
result.middle_cm + result.lower_cm, 2)
data["landmarks"]["hairline"] = None
else:
base_px = vd["upper_court_px"] + vd["middle_court_px"] + vd["lower_court_px"]
# 接口6 是三庭:去掉顶庭相关字段(top_court_cm / ratios.top_court / landmarks.hair_top
data["four_courts"]["ratios"] = {
"upper_court": round(vd["upper_court_px"] / base_px, 3),
"middle_court": round(vd["middle_court_px"] / base_px, 3),
"lower_court": round(vd["lower_court_px"] / base_px, 3),
}
data["four_courts"].pop("top_court_cm", None)
data["face_total_height_cm"] = round(
result.upper_cm + result.middle_cm + result.lower_cm, 2)
# 注:landmarks.hair_top 保留返回(供前端/下游定位头顶),但顶庭数值、
# 占比、标注图仍按三庭处理,显示效果不变。
# 七眼段宽度(cm)。eye1=左耳外段 eye2=左脸颊 eye3=左眼 eye4=两眼间距 eye5=右眼 eye6=右脸颊 eye7=右耳外段。
# eye2~eye6(5段)只用内部分点,接口1/6 共用;eye1/eye7 需耳朵分割端线,仅接口1 有。
@@ -389,11 +445,14 @@ def _run_face_measure_data(image, variant="v1"):
data["seven_eyes"][f"eye{i + 2}"] = (
None if (a is None or b is None) else round((b - a) / pc, 2))
if variant != "v6":
# 接口1 额外算 eye1/eye7(左/右耳外段),需耳朵分割端线
# 接口1 额外算 eye1/eye7(左/右耳外段),需耳朵分割端线
# 竖向范围:发际线弃用时用眉心做上界(hair_top 不可靠),否则用头顶。
from face_analysis.annotation import _ear_edges_from_mask
top_y = (vd["brow_center"][1] if discarded
else vd["hair_top"][1])
head_l, head_r = _ear_edges_from_mask(
ear_mask, hair_mask,
result.vertical["hair_top"][1], result.vertical["chin_tip"][1],
top_y, vd["chin_tip"][1],
lcx, rcx, (lcx + rcx) / 2)
data["seven_eyes"]["eye1"] = (
None if (head_l is None) else round((lcx - head_l) / pc, 2))
@@ -468,7 +527,7 @@ async def _face_measure_impl(image_file, image_url, image_base64, variant="v1"):
**标注图片 UI 规范**(真实版本生效):
- 字体/线条/箭头颜色:`#FFFFFF 100%`,透明底
- 字号/线宽/虚线/箭头按图片短边自适应缩放
- 四庭数值(名+数值两行,不带 cm)在图片**左侧**呈现,七眼段宽**上下穿插**展示,底部标「单位cm」
- 四庭(名 + 数值带cm + 百分比 三行)在图片**左侧**呈现,七眼段宽**上下穿插**展示(数值带cm,下方另起一行标占头宽百分比)
- 横线/竖线渐变消失并略超出端点;段宽/庭高用虚线 + 实心三角双箭头标示
- 竖线含人头最左/最右端线(取自头发分割轮廓),共 8 线 7 段
""",
@@ -573,7 +632,7 @@ async def face_measure(
**标注图片 UI 规范**(真实版本生效):
- 字体/线条/箭头颜色:`#FFFFFF 100%`,透明底
- 字号/线宽/虚线/箭头按图片短边自适应缩放
- 三庭数值(名+数值两行,不带 cm)在图片**左侧**呈现,七眼段宽**上下穿插**展示,底部标「单位cm」
- 三庭(名 + 数值带cm + 百分比 三行)在图片**左侧**呈现,七眼段宽**上下穿插**展示(数值带cm,下方另起一行标占头宽百分比)
- 段宽/庭高用虚线 + 实心三角双箭头标示
""",
responses={
@@ -716,7 +775,7 @@ async def hair_grow(
hair_style: Optional[str] = Form(default=None, description="发型序号逗号分隔(必填),如 1,2,3。female:1-5 male:1-4"),
beauty_enabled: bool = Form(default=False, description="是否开启美颜(本期不生效)"),
use_mask: bool = Form(default=True, description="是否启用 inpaint 遮罩(测试对比用)。false 时用干净原图生成(空遮罩,不烧模板线)"),
prompt: str = Form(default="充遮罩区域的头发,加一点美颜", description="ComfyUI 提示词,会替换工作流节点60的文本"),
prompt: str = Form(default="充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜", description="ComfyUI 提示词,会替换工作流节点60的文本"),
):
# 1. gender 必填校验(非法/缺失 → 1004)
if gender not in ("male", "female"):
@@ -769,117 +828,15 @@ async def hair_grow(
# ---------------------------------------------------------------------------
# 接口 7C 端生发 v2add_hair2.json 工作流)
# 接口 7C 端生发 v2 —— 已弃用add_hair2.json 用 Klein-9b 大模型,会把常驻的
# Klein-4b/Flux 挤出显存,导致接口2/3/5 耗时抖动;且业务已不再调用)。
# 保留路由返回明确错误,避免老客户端拿到裸 404。
# ---------------------------------------------------------------------------
_WORKFLOW2_PATH = os.path.join(os.path.dirname(__file__), "add_hair2.json")
@app.post(
"/api/v1/hair/grow-v2",
summary="接口7 C端生发 v2add_hair2 工作流)",
tags=["生发"],
description=f"""
输入用户正面照 + **性别** + **发型序号**,使用 add_hair2.json 工作流生成指定发际线类型的预览图与生发图。
功能与接口2 完全一致,仅 ComfyUI 工作流不同。
{_image_fields_desc}
图片同时支持 `multipart/form-data` 文件上传(字段名 `image_file`)。
---
- **gender**(必填):`male` / `female`。决定返回的贴图集合(female 5 张 / male 4 张)。
非法或缺失返回 `1004`。
- **hair_style**(必填):`int`,发型序号。`female`1=ellipse, 2=flower, 3=heart, 4=straight, 5=wave
`male`1=ellipse, 2=inverse_arc, 3=m, 4=straight。越界返回 `1007`。
- **beauty_enabled**:本期保留但不生效。
`hairline_type` 取值:`ellipse` / `flower` / `heart` / `straight` / `wave`female),
`ellipse` / `m` / `straight` / `inverse_arc`male)。
""",
responses={
200: {
"description": "成功",
"content": {
"application/json": {
"example": {
"code": 0,
"message": "success",
"request_id": "mock-request-id",
"data": {
"results": [
{"image_base64": "iVBORw0KGgo...", "hairline_type": "ellipse", "order": 1},
]
},
}
}
},
},
400: {
"description": "参数错误 / 图片识别失败",
"content": {
"application/json": {
"examples": {
"图片参数错误": {"value": {"code": 1007, "message": "图片参数错误:必须且只能传 image_file / image_url / image_base64 其中一个", "request_id": "x", "data": None}},
"非正面照": {"value": {"code": 1003, "message": "角度问题,请上传正面照", "request_id": "x", "data": None}},
}
}
},
},
},
)
async def hair_grow_v2(
image_file: Optional[UploadFile] = File(default=None, description="上传图片文件(JPG/PNG"),
image_url: Optional[str] = Form(default=None, description="图片 URL"),
image_base64: Optional[str] = Form(default=None, description="图片 base64(需带 data:image/...;base64, 前缀)"),
gender: Optional[str] = Form(default=None, description="性别 male/female(必填)"),
hair_style: Optional[str] = Form(default=None, description="发型序号逗号分隔(必填),如 1,2,3。female:1-5 male:1-4"),
beauty_enabled: bool = Form(default=False, description="是否开启美颜(本期不生效)"),
use_mask: bool = Form(default=True, description="是否启用 inpaint 遮罩(测试对比用)。false 时用干净原图生成(空遮罩,不烧模板线)"),
prompt: str = Form(default="补充遮罩区域的头发,加一点美颜", description="ComfyUI 提示词,会替换工作流节点60的文本"),
):
# 1. gender 必填校验(非法/缺失 → 1004)
if gender not in ("male", "female"):
return err(1004, "gender 必填且只能为 male / female")
# 2. hair_style 必填校验(解析逗号分隔,越界 → 1007)
max_styles = {"female": 5, "male": 4}[gender]
hair_styles = _parse_hair_styles(hair_style, max_styles)
if hair_styles is None:
return err(1007, f"hair_style 必填且为 1..{max_styles} 的整数(逗号分隔),收到 {hair_style!r}")
# 3. 三选一取图
raw, e = await resolve_image_bytes(image_file, image_url, image_base64)
if e is not None:
return e
image = cv2.imdecode(np.frombuffer(raw, np.uint8), cv2.IMREAD_COLOR)
if image is None:
return err(1008, "图片格式不支持(仅 JPG / PNG)")
try:
from fastapi.concurrency import run_in_threadpool
from hairline.service import generate_grow_results
# 预览 + 生发(ComfyUI) 都是阻塞且较慢,放线程池避免卡住事件循环
items = await run_in_threadpool(generate_grow_results, image, gender, use_mask, prompt, hair_styles, _WORKFLOW2_PATH)
if items is None:
return err(1001, "无法识别人像")
results = []
for p in items:
results.append({
"image_base64": _jpg_b64(p["image_bgr"]), # 预览图 JPG
"grown_image_base64": (_png_to_jpg_b64(p["grown_png"]) # 生发图 JPG
if p["grown_png"] else None),
"hairline_type": p["hairline_type"],
"order": p["order"],
})
return ok({"results": results})
except Exception as ex: # noqa: BLE001
logger.exception("接口7 处理异常")
return err(1007, f"处理失败:{ex}")
@app.post("/api/v1/hair/grow-v2", include_in_schema=False, deprecated=True)
async def hair_grow_v2():
"""接口7 已弃用:请改用 /api/v1/hair/grow(接口2)。"""
return err(1007, "接口7/api/v1/hair/grow-v2)已弃用,请使用 /api/v1/hair/grow")
# ---------------------------------------------------------------------------
@@ -929,7 +886,7 @@ async def hair_grow_b(
marked_image_url: Optional[str] = Form(default=None, description="划线图片 URL"),
marked_image_base64: Optional[str] = Form(default=None, description="划线图片 base64"),
use_mask: bool = Form(default=True, description="是否画发际线(测试对比用)。false 时跳过划线检测、直接送划线图"),
prompt: str = Form(default="充遮罩区域的头发,加一点美颜", description="ComfyUI 提示词,会替换工作流节点60的文本"),
prompt: str = Form(default="充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜", description="ComfyUI 提示词,会替换工作流节点60的文本"),
):
# 划线图三选一取图(只需这一张)
marked_raw, e = await resolve_image_bytes(marked_image_file, marked_image_url, marked_image_base64)
@@ -1060,6 +1017,8 @@ async def face_features(
`female`1=ellipse,2=flower,3=heart,4=straight,5=wave`male`1=ellipse,2=inverse_arc,3=m,4=straight。
- 可选 `use_mask` / `prompt`:同接口2 的生发控制参数。
注:生发黑模板固定取 `hairline_texture_black/`middle 档),即三档叠图分别用各自贴图、但生发目标固定 middle。
- 可选 `generate_grow_image`(默认 `true`):是否生成生发效果图(ComfyUI 生发,全流程最耗时)。
`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,大幅降低耗时。
**返回说明**
@@ -1137,7 +1096,8 @@ async def hairline_generate(
gender: Optional[str] = Form(default=None, description="性别 male/female(必填)"),
hair_style: Optional[str] = Form(default=None, description="发型序号逗号分隔(必填,如 1,2,3)。female:1-5 male:1-4"),
use_mask: bool = Form(default=True, description="生发是否启用 inpaint 遮罩(同接口2,测试对比用)"),
prompt: str = Form(default="充遮罩区域的头发,加一点美颜", description="ComfyUI 提示词(同接口2),会替换工作流节点60的文本"),
prompt: str = Form(default="充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜", description="ComfyUI 提示词(同接口2),会替换工作流节点60的文本"),
generate_grow_image: bool = Form(default=True, description="是否生成生发效果图(ComfyUI 生发,最耗时)。默认 true 出图;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"),
):
if gender not in ("male", "female"):
return err(1004, "gender 必填且只能为 male / female")
@@ -1161,7 +1121,8 @@ async def hairline_generate(
from hairline.service import generate_hairline_pngs
res = await run_in_threadpool(
generate_hairline_pngs, image, gender, hair_styles, use_mask, prompt)
generate_hairline_pngs, image, gender, hair_styles, use_mask, prompt,
generate_grow_image=generate_grow_image)
if res is None:
return err(1001, "无法识别人像")
@@ -1529,7 +1490,7 @@ async def hairline_grow_v2(
inpainting_fill: int = Form(default=1, description="change_hair服务端重绘填充:0=保留原图 | 1=噪声 | 2=纯色 | 3=潜变量。默认 1"),
mask_blur: int = Form(default=11, description="change_hair服务端遮罩边缘模糊像素,默认 11"),
mask_dilate_scale: float = Form(default=1.0, description="change_hair服务端遮罩膨胀缩放,默认 1.0"),
comfyui_prompt: Optional[str] = Form(default=None, description="Flux-2 重绘提示词,None 用默认「充遮罩区域的头发,加一点美颜」"),
comfyui_prompt: Optional[str] = Form(default=None, description="Flux-2 重绘提示词,None 用默认「充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜」"),
beauty_alpha: float = Form(default=0.6, description="redraw_band 版 band 外的全脸美颜融入强度(0=band外无美颜纯用final,1≈整帧版),默认 0.6"),
band_lo_mult: float = Form(default=0.5, description="重绘带外推倍率下限(相对 hairline_push_cm,内轮廓=0×、原外推线=1.0×),默认 0.5"),
band_hi_mult: float = Form(default=1.5, description="重绘带外推倍率上限(相对 hairline_push_cm),默认 1.5"),
@@ -1676,6 +1637,42 @@ async def hairline_grow_v2_final_v2(
return await _run_v2_final(image_file, image_url, image_base64, hairline_id, "接口12finalv2")
# ---------------------------------------------------------------------------
# 重绘端点(替代 local_test /api/generate
# ---------------------------------------------------------------------------
@app.post(
"/api/v1/redraw",
summary="ComfyUI 重绘",
tags=["重绘"],
description="""
传入人物图片 + 遮罩图片,直接调 ComfyUI0716add-hair 工作流)执行局部重绘。
替代原 local_test :8899 的 /api/generate 接口。
**遮罩图片格式**:支持红色遮罩(R=255)、白色遮罩(R=G=B=255)、Alpha遮罩(A=255),服务取所有通道最大值。
**遮罩区域**表示需要重绘的部分,非遮罩区域保持原图不变。
""",
)
async def api_redraw(
image_file: UploadFile = File(..., description="人物图片(JPG/PNG"),
mask_file: UploadFile = File(..., description="遮罩图片(PNG,支持红/白/alpha 格式)"),
prompt: str = Form(default="填充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜",
description="ComfyUI 提示词"),
):
image_bytes = await image_file.read()
mask_bytes = await mask_file.read()
from fastapi.concurrency import run_in_threadpool
from hairline.redraw import run_redraw
try:
png_bytes = await run_in_threadpool(
run_redraw, image_bytes, mask_bytes, prompt)
except Exception as e: # noqa: BLE001
logger.warning("重绘失败: %s", e)
return err(500, f"重绘失败: {e}")
b64 = base64.b64encode(png_bytes).decode()
return ok({"image_base64": f"data:image/png;base64,{b64}"})
# ---------------------------------------------------------------------------
# 调试:下载后端日志(接口11 遮罩计算全过程)
# ---------------------------------------------------------------------------
+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
+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)
+9 -57
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):
@@ -211,6 +213,8 @@
| 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 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)。
@@ -405,6 +409,7 @@
| 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,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。
@@ -426,7 +431,7 @@
| 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** URL(ComfyUI「植发」效果图,完整人像照片,生发失败时为 `null` |
| grown_image_url | string \| null | **生发后图片** URL(ComfyUI「植发」效果图,完整人像照片,生发失败`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`。
@@ -443,6 +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。
@@ -508,60 +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) |
| 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
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 | 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) |
| 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 |
| 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 |
@@ -572,7 +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 |
---
+49 -31
View File
@@ -6,9 +6,9 @@
- 纵向竖线 8 条: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 段(七眼),段宽数值上下交替(上 3 / 下 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 点 5 段)。
- 四庭:图片左侧,「名」「数值」下两行换行(不带 cm,带竖向虚线双箭头。
- 四庭:图片左侧,「名」「数值(带 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 B,BiSeNet 类 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(顶/上/中/下庭)在左侧:名 + 数值两行换行(无 cm,竖向虚线双箭头。
- 七眼段宽数值上下交替(上 3 / 下 4,无 cm),横向虚线双箭头。
- 底部统一标「单位cm」。
- 四庭(顶/上/中/下庭)在左侧:名 + 数值(带 cm) + 百分比三行换行,竖向虚线双箭头。
- 七眼段宽上下交替(上 3 / 下 4):数值(带 cm) 上、百分比(占头宽比)下,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 条
横线 + 上/中/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)
+86 -76
View File
@@ -102,11 +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)。
供 ComfyUI 重绘接口(/api/v1/redraw)按 alpha 通道识别重绘区。
注意:cv2.imencode 写 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)
# ---------------------------------------------------------------------------
@@ -342,7 +357,8 @@ def _redraw_band_mask(inner_pts, outer_pts, h, w, rid="", upper=None,
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。
@@ -350,6 +366,10 @@ def compute_mask(image_bgr, landmarks, seg_model, mask_type, erode_cm, px_per_cm
hairline_push_cm: 仅 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: 仅 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+ 张 base64 编码,省 ~80ms;数据字段(_inner_pts/_outer_pts/_upper_mask/
mask_pixels 等)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,省 ~0.9s。
返回 (mask_bool, viz_dict)。
"""
lg = lambda msg: logger.info("[%s] %s", rid, msg) if rid else None
@@ -363,13 +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
@@ -410,47 +433,49 @@ 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(_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)
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
@@ -578,7 +603,7 @@ _REPAINT_WORKFLOW = os.path.join(os.path.dirname(os.path.dirname(__file__)), "ha
def _call_comfyui(image_bgr, mask_bool, prompt=None):
"""本机 ComfyUI 的 Flux-2 inpaint 工作流(hair_repaint.json),返回与输入同分辨率的 BGR。
"""远端 ComfyUI 的 Flux-2 inpaint 工作流(hair_repaint.json),返回与输入同分辨率的 BGR。
与 swapHair 的区别:ComfyUI 把「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 经 RGBA alpha 通道传入(透明=重绘区)。
@@ -586,10 +611,10 @@ def _call_comfyui(image_bgr, mask_bool, prompt=None):
"""
import io
from hairline.mask import compose_comfy_rgba
from hairline.comfyui import run as comfyui_run, ping
from hairline.comfyui import COMFYUI_URL, run as comfyui_run, ping
if not ping():
raise SwapError("ComfyUI 不可达(http://127.0.0.1:8188),redraw Flux-2 路跳过")
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()
@@ -829,7 +854,8 @@ 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):
inpainting_fill, mask_blur, mask_dilate_scale, rid, render_viz=True,
hair_mask=None):
"""接口11 共享核心:遮罩(pushed)→生成→硬贴回→接缝融合,产出 ④ final。
不做任何重绘。返回中间产物 dict(供接口11 构造响应、接口12 取 final+重绘带用):
@@ -858,7 +884,8 @@ def _grow_core(image_bgr, hairline_id, *, is_hr, seg_model, erode_cm, swap_mode,
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()))
@@ -1007,21 +1034,20 @@ def generate_hairline_redraw(image_bgr, hairline_id, is_hr=False, seg_model="seg
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):
band_lo_mult=0.5, band_hi_mult=1.5, rid=None,
hair_mask=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、经 baseline 截断只留上部)作遮罩,用 Flux-2ComfyUIhair_repaint.json
重绘(band 经 alpha 送进 ComfyUI 决定加发位置,ComfyUI 输出为整帧重绘+美颜图)。
(外推↔内推之间、经 baseline 截断只留上部)作遮罩
**同时产出两版结果供对比**
- `redraw_full`ComfyUI 整帧输出(全脸美颜 + 全脸重绘),与手动跑 ComfyUI 一致。
- `redraw_band`:加发只在发际线带、美颜保留全脸。band 内完全用 ComfyUI 重绘(加发),
band 外用 `final` 结构 + 按 `beauty_alpha` 融入 ComfyUI 的全脸美颜
**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() 的 data dict。未检出人脸抛 NoFaceError。
comfyui_promptFlux-2 提示词,None 用默认「补充遮罩区域的头发,加一点美颜」
beauty_alpharedraw_band 版 band 外的全脸美颜融入强度(0=完全保留 final 无美颜,
1=band 外也完全用 ComfyUI 输出≈redraw_full),默认 0.6。
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)。
@@ -1037,7 +1063,8 @@ def generate_hairline_redraw(image_bgr, hairline_id, is_hr=False, seg_model="seg
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)
mask_dilate_scale=mask_dilate_scale, rid=rid, render_viz=False,
hair_mask=hair_mask)
final = core["final"]
mask_viz = core["mask_viz"]
w, h = core["w"], core["h"]
@@ -1050,8 +1077,7 @@ def generate_hairline_redraw(image_bgr, hairline_id, is_hr=False, seg_model="seg
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_full_b64 = "" # A:ComfyUI 整帧(全脸美颜+全脸重绘
redraw_band_b64 = "" # B:加发只在发际线带、美颜保留全脸
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:
@@ -1062,44 +1088,26 @@ def generate_hairline_redraw(image_bgr, hairline_id, is_hr=False, seg_model="seg
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 路:final + band 调 ComfyUIhair_repaint.json 整图重绘 + reference latent
# 保色 + ColorMatch + 美颜)。band 经 alpha 送进 ComfyUI 决定加发位置
beauty_alpha = float(min(max(beauty_alpha, 0.0), 1.0))
if redraw_info.get("enabled"):
try:
prompt = comfyui_prompt if comfyui_prompt else "补充遮罩区域的头发,加一点美颜"
redraw_c_raw = _call_comfyui(final, band_mask, prompt=prompt)
# A:整帧输出(与手动跑 ComfyUI 一致)
redraw_full_b64 = _jpg_b64(redraw_c_raw)
# B:加发只在 band、美颜保留全脸。
# alpha = band 内 1(羽化边缘);band 外 = beauty_alpha。
# band 内完全用 ComfyUI(加发);band 外用 final 结构 + beauty_alpha 融入全脸美颜。
feather_px = max(8, int(round(push_px * 0.6)))
band_a = _feather_alpha(band_mask, "feather", feather_px, 0) # 0..1band 外=0
a = band_a + (1.0 - band_a) * beauty_alpha
a3 = a[:, :, None]
band_mix = (final.astype(np.float32) * (1.0 - a3)
+ redraw_c_raw.astype(np.float32) * a3)
redraw_band_b64 = _jpg_b64(np.clip(band_mix, 0, 255).astype(np.uint8))
redraw_info["beauty_alpha"] = beauty_alpha
logger.info("[%s] Flux-2 重绘完成:redraw_full(整帧) + redraw_band(局部加发+全脸美颜 beauty_alpha=%.2f)",
rid, beauty_alpha)
except Exception as ex: # noqa: BLE001
logger.warning("[%s] Flux-2 路重绘失败,跳过: %s", rid, ex)
redraw_info["c_error"] = str(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 "充遮罩区域的头发,加一点美颜",
"comfyui_prompt": comfyui_prompt or "充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜",
"beauty_alpha": beauty_alpha,
"px_per_cm": round(float(px_per_cm), 4),
"mask_pixels": mask_viz["mask_pixels"],
@@ -1116,9 +1124,11 @@ def generate_hairline_redraw(image_bgr, hairline_id, is_hr=False, seg_model="seg
"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,
# A:ComfyUI 整帧重绘+美颜(与手动跑 ComfyUI 一致
# 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
# 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,
+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
+1 -1
View File
@@ -410,7 +410,7 @@
},
"60": {
"inputs": {
"text": "充遮罩区域的头发,加一点美颜"
"text": "充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜"
},
"class_type": "JjkText",
"_meta": {
+21 -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」的 RGBA 上传到本机 ComfyUI(默认 8188)
worker 不跑 Flux,只把「划线图 + 遮罩」的 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
@@ -84,11 +86,13 @@ 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) -> bytes:
"""提交一次生发任务,返回输出 PNG 字节。失败抛异常。
prompt:非 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 端 "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。
"""
path = workflow_path or _WORKFLOW_DEFAULT
output_node = _get_output_node(path)
@@ -103,6 +107,14 @@ 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)
@@ -124,8 +136,11 @@ def run(rgba_png_bytes: bytes, timeout: float = COMFY_TIMEOUT, prompt: str = Non
except Exception: # noqa: BLE001
pass
# 3. 提交
r = cli.post("/prompt", json={"prompt": wf, "client_id": client_id})
# 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"]
@@ -144,7 +159,7 @@ 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(见 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 成「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,取 silhouette
SegFormer skinhair 类,近似头部实际轮廓)上沿 y,若点比这个上沿还高(y 更
小),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.
#
+78
View File
@@ -0,0 +1,78 @@
"""直接调 ComfyUI 重绘 — 替代 local_test HTTP 服务。
将 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,皮肤加一点磨皮,再加一点美颜"
_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 为 RGB
2. 加载 mask 为 RGBA,取所有通道 max 值(支持红/白/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) -> 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/白/alpha 遮罩格式)
prompt: 提示词,None 用默认 "填充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜"
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)
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)
+197 -28
View File
@@ -14,7 +14,9 @@ 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
@@ -40,6 +42,48 @@ _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,皮肤加一点磨皮,再加一点美颜")
# 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):
"""直接调 ComfyUI 重绘(替代原 local_test HTTP 服务)。
传 final 图 + 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)。
"""
from .redraw import run_redraw
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 _REDRAW_MAX_SIDE > 0 and m > _REDRAW_MAX_SIDE:
scale = _REDRAW_MAX_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, _REDRAW_MAX_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=_REDRAW_PROMPT, front=True)
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,
@@ -47,9 +91,8 @@ _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
@@ -111,13 +154,19 @@ 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(如 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)
@@ -182,9 +231,14 @@ 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)
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)
@@ -202,9 +256,14 @@ 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)
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)
@@ -215,23 +274,28 @@ def generate_grow_results(image_bgr: np.ndarray, gender: str, use_mask: bool = T
def generate_grow_results_swap(image_bgr: np.ndarray, hair_styles: list[int] | None,
redraw_defaults: dict):
"""接口2 女性专用:发际线透明叠图(同 generate_grow_results+ 换发型+Flux-2 整帧重绘图。
"""接口2 女性专用:发际线透明叠图(同 generate_grow_results+ 换发型重绘图。
与 generate_grow_results 的差异仅在 grown 图来源:这里对每个选中发型把 female key 映射到
change_hair 的 chang_* hair_id调 face_analysis.hairline_grow.generate_hairline_redraw
(= 接口12 final 管线,参数用 redraw_defaults),取 `redraw_full`(整帧重绘)作为生发图。
grown 图来源(新流程):对每个选中发型把 female key 映射到 change_hair 的 chang_* hair_id
调 face_analysis.hairline_grow.generate_hairline_redraw(= 接口12 final 管线,参数用
redraw_defaults)拿到 ④ final(接缝融合基底)+ ⑤-② 纯红遮罩 PNG,再**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(与 generate_grow_results 完全一致)。
Returns: list[dict] {"hairline_type","order","overlay","grown_png"(jpg bytes 或 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]
@@ -240,6 +304,20 @@ def generate_grow_results_swap(image_bgr: np.ndarray, hair_styles: list[int] | N
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。
redraw_img = image_bgr
hair_mask_redraw = hair_mask_reuse
if _REDRAW_MAX_SIDE > 0 and max(h, w) > _REDRAW_MAX_SIDE:
redraw_img, _rs = _downscale_max_side(image_bgr, _REDRAW_MAX_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, _REDRAW_MAX_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)
@@ -250,13 +328,39 @@ def generate_grow_results_swap(image_bgr: np.ndarray, hair_styles: list[int] | N
logger.warning("接口2 换发型:female key=%s 无对应 chang_id,跳过生发图", key)
else:
try:
data = generate_hairline_redraw(image_bgr, chang_id, **redraw_defaults)
b64 = (data.get("steps") or {}).get("redraw_full_base64") or ""
if b64.startswith("data:"):
b64 = b64.split(",", 1)[1]
grown_png = base64.b64decode(b64) if b64 else None
if grown_png is None:
logger.warning("接口2 换发型:type=%s 整帧重绘为空(可能 ComfyUI 未生效)", key)
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)
_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
@@ -283,7 +387,7 @@ 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)
@@ -292,13 +396,16 @@ 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):
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,RGBA 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 档。
use_mask/prompt:同接口2 的生发参数。
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。
@@ -320,8 +427,9 @@ 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)
def _center_of(overlay):
@@ -340,9 +448,13 @@ def generate_hairline_pngs(image_bgr: np.ndarray, gender: str,
for lv in _TEXTURE_DIRS:
white = load_texture_rgba(tex_by_level[lv][s - 1][1])
overlays[lv] = build_overlay_layer(h, w, 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)
# 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_centers:首个选中发型三档(middle/high/low)发际线中点
@@ -351,18 +463,73 @@ def generate_hairline_pngs(image_bgr: np.ndarray, gender: str,
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):
"""接口3:检测医生手绘发际线 → 遮罩 → 送 ComfyUI 生发(仅需划线图一张)。
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)。
进 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=255−mask(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 全 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 或 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)
@@ -380,8 +547,10 @@ 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"}
+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,皮肤加一点磨皮" |
#### 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,皮肤加一点磨皮" \
--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,皮肤加一点磨皮"
}
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,皮肤加一点磨皮,再加一点美颜")
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,皮肤加一点磨皮,再加一点美颜")
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,皮肤加一点磨皮,再加一点美颜")
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,皮肤加一点磨皮,再加一点美颜", 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,皮肤加一点磨皮,再加一点美颜">
</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,皮肤加一点磨皮,再加一点美颜"},
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

+86
View File
@@ -0,0 +1,86 @@
// 上传图片自动降采样:当总像素 > MAX_PIXELS 时,等比例缩小到 <= TARGET_PIXELS。
// 用法:在提交前 file = await window.downscaleImageFile(file);
(function () {
var MAX_PIXELS = 1536000; // 触发阈值:超过则缩小
var TARGET_PIXELS = 786432; // 缩小后总像素上限
function loadImage(url) {
return new Promise(function (resolve, reject) {
var img = new Image();
img.onload = function () { resolve(img); };
img.onerror = reject;
img.src = url;
});
}
async function downscaleImageFile(file) {
// 非图片、GIF、SVG 不处理,原样返回
if (!file || !file.type || file.type.indexOf('image/') !== 0) return file;
if (file.type === 'image/gif' || file.type === 'image/svg+xml') return file;
var url = URL.createObjectURL(file);
try {
var img = await loadImage(url);
var w = img.naturalWidth, h = img.naturalHeight;
var total = w * h;
if (!total || total <= MAX_PIXELS) return file; // 未超阈值,原图直接用
var scale = Math.sqrt(TARGET_PIXELS / total);
var nw = Math.max(1, Math.round(w * scale));
var nh = Math.max(1, Math.round(h * scale));
var canvas = document.createElement('canvas');
canvas.width = nw;
canvas.height = nh;
var ctx = canvas.getContext('2d');
ctx.drawImage(img, 0, 0, nw, nh);
var outType = file.type === 'image/png' ? 'image/png' : 'image/jpeg';
var quality = outType === 'image/jpeg' ? 0.92 : undefined;
var blob = await new Promise(function (res) { canvas.toBlob(res, outType, quality); });
if (!blob) return file;
var base = (file.name || 'image').replace(/\.(jpe?g|png|webp|bmp)$/i, '');
var name = base + (outType === 'image/png' ? '.png' : '.jpg');
return new File([blob], name, { type: outType, lastModified: Date.now() });
} catch (e) {
console.warn('downscaleImageFile 失败,使用原图', e);
return file;
} finally {
URL.revokeObjectURL(url);
}
}
window.downscaleImageFile = downscaleImageFile;
/**
* 将接口返回的图片字段规范成 <img src> 可用值。
* 同时兼容:
* - 网关改写后的 *_urlhttp/https/相对路径)
* - worker 直连的 *_base64(原始 base64,或已带 data:image/...;base64, 前缀)
* @param {string|null|undefined} url
* @param {string|null|undefined} b64
* @param {string} [mimeHint='image/jpeg'] 原始 base64 时的 MIME 提示(会按魔数再嗅探)
* @returns {string}
*/
function resolveImgSrc(url, b64, mimeHint) {
var v = url || b64 || '';
if (!v || typeof v !== 'string') return '';
v = v.trim();
if (!v) return '';
// 已是可用 URL / data URI / blob / 协议相对 URL
if (/^(https?:|blob:|data:|\/\/)/i.test(v)) return v;
// 同站相对路径(仅匹配明确的 /static/...;勿把 JPEG base64 的 /9j/ 前缀当路径)
if (/^\/static\//.test(v)) return v;
// 原始 base64:去掉可能残留的 data URI 前缀后再拼,避免双重前缀导致无法显示
var raw = v.replace(/^data:image\/[a-zA-Z0-9+.-]+;base64,/i, '');
if (!raw) return '';
var mime = mimeHint || 'image/jpeg';
if (raw.indexOf('iVBOR') === 0) mime = 'image/png';
else if (raw.indexOf('/9j/') === 0) mime = 'image/jpeg';
else if (raw.indexOf('R0lGOD') === 0) mime = 'image/gif';
else if (raw.indexOf('UklGR') === 0) mime = 'image/webp';
return 'data:' + mime + ';base64,' + raw;
}
window.resolveImgSrc = resolveImgSrc;
})();
+16 -40
View File
@@ -57,7 +57,6 @@
<a href="#if4">接口4</a>
<a href="#if5">接口5</a>
<a href="#if6">接口6</a>
<a href="#if7">接口7</a>
<a href="#errors">错误码</a>
<a href="#test">在线测试</a>
</div>
@@ -109,6 +108,8 @@
<tr><td><code>landmarks</code></td><td>object</td><td>5 个关键点像素坐标:hair_top/hairline/brow_center/nose_bottom/chin_tip</td></tr>
<tr><td><code>hairline_source</code></td><td>string</td><td>发际线来源:<code>"segmentation"</code>(真实分割,可信度高)/ <code>"estimated"</code>(比例估算,可信度低)</td></tr>
<tr><td><code>head_pose</code></td><td>object</td><td>头部姿态角度:<code>{ yaw, pitch, roll }</code>(度),接近 0 表示正面照</td></tr>
<tr><td><code>left_position</code></td><td>object</td><td>MediaPipe 21 号关键点坐标(左脸定位点),原图像素:<code>{ x: number, y: number }</code></td></tr>
<tr><td><code>right_position</code></td><td>object</td><td>MediaPipe 251 号关键点坐标(右脸定位点,与 21 号镜像),原图像素:<code>{ x: number, y: number }</code></td></tr>
</table>
<p style="margin-top:12px;font-size:12px;color:#64748b">💡 前端把标注图叠加到原图上即可呈现测量效果(标注图白色线条 #FFFFFF,透明底)。</p>
@@ -189,17 +190,17 @@ const { code, data } = await res.json();
<div class="card" id="if4">
<h2>4. 用户特征分析 &nbsp;<span class="badge post">POST</span> &nbsp;<code>/api/v1/face/features</code></h2>
<div class="card-body">
<p class="desc">上传照片 → 火山方舟豆包视觉模型分析 → 返回几十项面部特征(脸型/眉形/肤色/四季色彩…)。</p>
<p class="desc">上传照片 → 火山方舟豆包视觉模型分析 → 返回固定 6 项面部特征(脸型/眉形/面部年龄/动静类型/性别/基因风格)。</p>
<p><strong>入参</strong>image_file / image_url / image_base64 三选一。无其他参数。</p>
<p style="margin-top:12px"><strong>data 字段</strong></p>
<table>
<tr><th>字段</th><th>类型</th><th>说明</th></tr>
<tr><td><code>features</code></td><td>string</td><td><strong>JSON 字符串</strong>(不是对象!客户端需 <code>JSON.parse()</code></td></tr>
<tr><td><code>features</code></td><td>string</td><td><strong>JSON 字符串</strong>(不是对象!客户端需 <code>JSON.parse()</code>。解析后得到<strong>固定 6 个英文字段</strong></td></tr>
</table>
<p style="margin-top:8px"><strong>features 英文优先字段</strong>其余中文字段同时返回,共~42个):</p>
<p style="margin-top:8px"><strong>features 字段</strong>固定返回 6 个):</p>
<table>
<tr><th>字段</th><th>说明</th><th>字段</th><th>说明</th></tr>
<tr><td>face_shape</td><td>脸型</td><td>eyebrow_shape</td><td>眉形</td></tr>
@@ -214,7 +215,7 @@ const { code, data } = await res.json();
const { code, data } = await res.json();
const features = JSON.parse(data.features); // ← 注意:data.features 是字符串!
console.log(features.face_shape); // "鹅蛋脸"
console.log(features['四季色彩季型']); // "冷夏型"(中文字段也保留)</pre>
console.log(features.gene_style); // "自然型"</pre>
</div>
</div>
@@ -230,12 +231,13 @@ console.log(features['四季色彩季型']); // "冷夏型"(中文字段也保
<tr><td>image_file / image_url / image_base64</td><td></td><td>三选一</td><td>用户正面照</td></tr>
<tr><td>gender</td><td>string</td><td>✅ 必填</td><td><code>"male"</code> / <code>"female"</code></td></tr>
<tr><td>hair_style</td><td>string</td><td>✅ 必填</td><td>发型序号,逗号分隔多选(如 <code>1,2,3</code>)。缺失/越界返回 1007</td></tr>
<tr><td>generate_grow_image</td><td>bool</td><td></td><td>是否生成生发效果图(ComfyUI 生发,全流程最耗时),默认 <code>true</code>。传 <code>false</code> 时跳过生发,各发型 <code>grown_image_url</code> 恒为 <code>null</code>,仅返回三档发际线叠图与中心点,大幅降低耗时</td></tr>
</table>
<p style="margin-top:12px"><strong>data 字段</strong></p>
<table>
<tr><th>字段</th><th>类型</th><th>说明</th></tr>
<tr><td><code>hairline_images[]</code></td><td>object[]</td><td>选中发型列表,每项含 <code>hairline_type</code><code>image_middle_url</code>/<code>image_high_url</code>/<code>image_low_url</code> 三档<strong>透明 PNG 叠图</strong>(仅曲线,需叠加原图)、<code>grown_image_url</code> 生发图(完整人像,失败为 null)、<code>order</code></td></tr>
<tr><td><code>hairline_images[]</code></td><td>object[]</td><td>选中发型列表,每项含 <code>hairline_type</code><code>image_middle_url</code>/<code>image_high_url</code>/<code>image_low_url</code> 三档<strong>透明 PNG 叠图</strong>(仅曲线,需叠加原图)、<code>grown_image_url</code> 生发图(完整人像,失败<code>generate_grow_image=false</code>为 null)、<code>order</code></td></tr>
<tr><td><code>best_hairline_center_point</code></td><td>object \| null</td><td>首个选中发型 <strong>middle 档</strong>发际线中心点像素坐标 <code>{ x: number, y: number }</code></td></tr>
<tr><td><code>high_hairline_center_point</code></td><td>object \| null</td><td>同上,<strong>high 档</strong>发际线中点(发际线偏高,y 更小)</td></tr>
<tr><td><code>low_hairline_center_point</code></td><td>object \| null</td><td>同上,<strong>low 档</strong>发际线中点(发际线偏低,y 更大)</td></tr>
@@ -251,6 +253,8 @@ console.log(features['四季色彩季型']); // "冷夏型"(中文字段也保
<tr><td><code>landmarks</code></td><td>object</td><td>5 个关键点像素坐标:hair_top/hairline/brow_center/nose_bottom/chin_tip</td></tr>
<tr><td><code>hairline_source</code></td><td>string</td><td>发际线来源:<code>"segmentation"</code>(真实分割)/ <code>"estimated"</code>(比例估算)</td></tr>
<tr><td><code>head_pose</code></td><td>object</td><td>头部姿态角度:<code>{ yaw, pitch, roll }</code>(度)</td></tr>
<tr><td><code>left_position</code></td><td>object</td><td>MediaPipe 21 号关键点坐标(左脸定位点),原图像素:<code>{ x: number, y: number }</code></td></tr>
<tr><td><code>right_position</code></td><td>object</td><td>MediaPipe 251 号关键点坐标(右脸定位点,与 21 号镜像),原图像素:<code>{ x: number, y: number }</code></td></tr>
</table>
<p style="margin-top:12px;font-size:12px;color:#64748b">💡 前端无需额外请求接口1 即可拿到四庭七眼测量数值;<code>face_measure</code><code>null</code> 时(角度过大/无人脸等)仅隐藏测量区块,发际线结果照常展示。</p>
@@ -282,41 +286,12 @@ console.log(features['四季色彩季型']); // "冷夏型"(中文字段也保
<tr><td><code>four_courts</code></td><td>object</td><td>三庭:upper/middle/lower,各含 _cm 和 ratios<strong>无 top_court</strong></td></tr>
<tr><td><code>seven_eyes</code></td><td>object</td><td>七眼:<code>eye_width_cm</code>/<code>face_width_cm</code>/<code>inter_eye_distance_cm</code> + <code>ratios</code> + <strong><code>eye2</code>~<code>eye6</code></strong>(左脸颊/左眼/两眼间距/右眼/右脸颊,5 段宽度 cm;<strong>无 eye1/eye7</strong></td></tr>
<tr><td><code>landmarks</code></td><td>object</td><td>4 个关键点:hairline/brow_center/nose_bottom/chin_tip<strong>无 hair_top</strong></td></tr>
<tr><td><code>left_position</code></td><td>object</td><td>MediaPipe 21 号关键点坐标(左脸定位点),原图像素:<code>{ x: number, y: number }</code></td></tr>
<tr><td><code>right_position</code></td><td>object</td><td>MediaPipe 251 号关键点坐标(右脸定位点,与 21 号镜像),原图像素:<code>{ x: number, y: number }</code></td></tr>
</table>
</div>
</div>
<!-- ======== 接口7 ======== -->
<div class="card" id="if7">
<h2>7. C端生发 v2 &nbsp;<span class="badge post">POST</span> &nbsp;<code>/api/v1/hair/grow-v2</code> &nbsp;<span class="badge warn">v2</span></h2>
<div class="card-body">
<p class="desc">功能与<a href="#if2">接口2</a>完全一致,仅 ComfyUI 工作流不同——使用 <code>add_hair2.json</code> 替代 <code>add_hair.json</code>Flux-2 Klein 9b)。</p>
<p><strong>入参</strong></p>
<table>
<tr><th>参数</th><th>类型</th><th>必填</th><th>说明</th></tr>
<tr><td>image_file / image_url / image_base64</td><td></td><td>三选一</td><td>用户正面照</td></tr>
<tr><td>gender</td><td>string</td><td>✅ 必填</td><td><code>"male"</code> / <code>"female"</code></td></tr>
<tr><td>hair_style</td><td>int</td><td>✅ 必填</td><td>发型序号。female: 1~5male: 1~4</td></tr>
</table>
<p style="margin-top:12px"><strong>data.results[] 元素</strong>(同接口2</p>
<table>
<tr><th>字段</th><th>类型</th><th>说明</th></tr>
<tr><td><code>image_url</code></td><td>string</td><td>发际线曲线<strong>透明 PNG</strong>(仅曲线,需叠加原图显示,同接口2</td></tr>
<tr><td><code>grown_image_url</code></td><td>string</td><td>生发后效果图(完整人像)⚠ 可空</td></tr>
<tr><td><code>hairline_type</code></td><td>string</td><td>发际线类型 key</td></tr>
<tr><td><code>order</code></td><td>int</td><td>排序</td></tr>
</table>
<p style="margin-top:8px;font-size:12px;color:#64748b">
Female 5 种:ellipse/flower/heart/straight/wave &nbsp;|&nbsp;
Male 4 种:ellipse/m/straight/inverse_arc<br>
⚠ 工作流: add_hair2.jsonFlux-2 Klein 9b),输入节点 26,输出节点 75。
</p>
</div>
</div>
<!-- ======== 错误码 ======== -->
<div class="card" id="errors">
<h2>⚠ 错误码</h2>
@@ -326,12 +301,14 @@ console.log(features['四季色彩季型']); // "冷夏型"(中文字段也保
<tr><td>1001</td><td>无法识别人像</td><td>未检测到人脸</td></tr>
<tr><td>1003</td><td>角度问题,非正面照</td><td>非正面 / 角度过大</td></tr>
<tr><td>1004</td><td>gender 必填且只能为 male / female</td><td>接口2/5 的 <code>gender</code> 缺失或非法</td></tr>
<tr><td>1005</td><td>检测到多张人脸</td><td>仅支持单人</td></tr>
<tr><td>1007</td><td>图片参数错误 / 后端不可用</td><td>参数传错 / 服务繁忙请稍后重试</td></tr>
<tr><td>1008</td><td>图片格式不支持</td><td>非 JPG/PNG / base64 解码失败</td></tr>
<tr><td>1009</td><td>未授权</td><td>缺少或错误的 <code>X-Internal-Token</code><code>/api/*</code> 路径鉴权)</td></tr>
</table>
<p style="font-size:12px;color:#94a3b8;margin-top:8px">1004 已废弃(接口2 不再自动判性别,改由客户端传 gender 参数)</p>
<p style="font-size:12px;color:#94a3b8;margin-top:8px">注:1004 仍在使用(接口2/5 的 gender 校验);接口7(grow-v2)已弃用,请改用接口2</p>
</div>
</div>
@@ -344,10 +321,9 @@ console.log(features['四季色彩季型']); // "冷夏型"(中文字段也保
<tr><td>1. 四庭七眼</td><td><a href="/static/test_interface1.html" class="link">/static/test_interface1.html</a></td><td>上传照片 → 原图+标注叠加,底图/标注开关,指标卡片</td></tr>
<tr><td>2. C端生发</td><td><a href="/static/test_interface2.html" class="link">/static/test_interface2.html</a></td><td>上传+性别 → 方案一覧(原图/叠加/生发),双图对比</td></tr>
<tr><td>3. B端生发</td><td><a href="/static/test_interface3.html" class="link">/static/test_interface3.html</a></td><td>划线图上传 → 生发效果图</td></tr>
<tr><td>4. 用户特征</td><td><a href="/static/test_interface4.html" class="link">/static/test_interface4.html</a></td><td>上传照片 → 42项面部特征表格 + 原始JSON</td></tr>
<tr><td>4. 用户特征</td><td><a href="/static/test_interface4.html" class="link">/static/test_interface4.html</a></td><td>上传照片 → 6项面部特征 + 原始JSON</td></tr>
<tr><td>5. 发际线PNG</td><td><a href="/static/test_interface5.html" class="link">/static/test_interface5.html</a></td><td>上传+性别 → 发际线方案+中心点坐标</td></tr>
<tr><td>6. 四庭七眼 v2</td><td><a href="/static/test_interface6.html" class="link">/static/test_interface6.html</a></td><td>同接口1,去顶庭 · 竖线发际线→下巴 · 无头部端线</td></tr>
<tr><td>7. C端生发 v2</td><td><a href="/static/test_interface7.html" class="link">/static/test_interface7.html</a></td><td>同接口2,使用 add_hair2.json 工作流(Flux-2 Klein 9b</td></tr>
</table>
<p style="font-size:12px;color:#94a3b8;margin-top:12px">
完整 API 文档:<a href="/docs" class="link">/docs</a>Swagger UI
+12 -3
View File
@@ -62,6 +62,7 @@
@media (max-width: 768px) { .results { flex-direction: column; } }
.hidden { display: none !important; }
</style>
<script src="/static/img_downscale.js?v=2"></script>
</head>
<body>
<div class="container">
@@ -127,8 +128,9 @@ function setStatus(text, type) {
async function submitTest() {
const fileInput = $('imageFile');
const file = fileInput.files[0];
let file = fileInput.files[0];
if (!file) { setStatus('请先选择一张图片', 'error'); return; }
file = await window.downscaleImageFile(file);
const _reqStart = performance.now();
@@ -148,7 +150,7 @@ async function submitTest() {
form.append('image_file', file);
try {
const resp = await fetch(API_BASE + '/api/v1/face/measure', { method: 'POST', body: form });
const resp = await fetch(API_BASE + '/api/v1/face/measure', { method: 'POST', headers: { 'X-Internal-Token': 'dev-shared-secret-2026' }, body: form });
const json = await resp.json();
const _elapsed = ((performance.now() - _reqStart) / 1000).toFixed(2);
@@ -157,7 +159,10 @@ async function submitTest() {
if (json.code === 0) {
setStatus('✅ 请求成功 (' + _elapsed + 's) — request_id: ' + json.request_id, 'success');
showOverlay(json.data.annotated_image_url);
// 兼容本地直连 worker*_base64)与网关(*_url
const _d = json.data || {};
const annoUrl = resolveImgSrc(_d.annotated_image_url, _d.annotated_image_base64, 'image/png');
showOverlay(annoUrl);
renderMetrics(json.data);
$('metricsBar').classList.remove('hidden');
} else {
@@ -182,6 +187,10 @@ function showOverlay(annoUrl) {
setTimeout(() => showOverlay(annoUrl), 200);
return;
}
if (!annoUrl) {
$('imgPanel').innerHTML = '<span class="placeholder">后端未返回标注图(annotated_image_base64 为空)</span>';
return;
}
const checked = $('showAnno').checked ? '' : 'display:none';
const opacity = ($('annoOpacity').value / 100).toFixed(2);
+4 -2
View File
@@ -50,6 +50,7 @@
.lightbox { position: fixed; inset: 0; background: rgba(0,0,0,.85); display: none; align-items: center; justify-content: center; z-index: 50; cursor: zoom-out; }
.lightbox img { max-width: 95%; max-height: 95%; }
</style>
<script src="/static/img_downscale.js"></script>
</head>
<body>
<div class="container">
@@ -197,8 +198,9 @@ function renderMetrics(data) {
}
async function submitTest() {
const file = $('imageFile').files[0];
let file = $('imageFile').files[0];
if (!file) { setStatus('请先选择一张图片', 'error'); return; }
file = await window.downscaleImageFile(file);
const t0 = performance.now();
const btn = $('submitBtn');
@@ -212,7 +214,7 @@ async function submitTest() {
form.append('dilate_cm', $('dilateCm').value || '2.0');
try {
const resp = await fetch(API_BASE + ENDPOINT, { method: 'POST', body: form });
const resp = await fetch(API_BASE + ENDPOINT, { method: 'POST', headers: { 'X-Internal-Token': 'dev-shared-secret-2026' }, body: form });
const json = await resp.json();
const dt = ((performance.now() - t0) / 1000).toFixed(2);
+3 -1
View File
@@ -55,6 +55,7 @@
.lightbox { position: fixed; inset: 0; background: rgba(0,0,0,.85); display: none; align-items: center; justify-content: center; z-index: 50; cursor: zoom-out; }
.lightbox img { max-width: 95%; max-height: 95%; }
</style>
<script src="/static/img_downscale.js"></script>
</head>
<body>
<div class="container">
@@ -292,8 +293,9 @@ function renderResult(d) {
}
async function submitTest() {
const file = $('imageFile').files[0];
let file = $('imageFile').files[0];
if (!file) { setStatus('请先选择一张图片', 'error'); return; }
file = await window.downscaleImageFile(file);
const t0 = performance.now();
const btn = $('submitBtn');
btn.disabled = true; btn.textContent = '⏳ 请求中...';
+69 -20
View File
@@ -34,8 +34,12 @@
.status.success { background: #d1fae5; color: #065f46; display: block; }
.steps { display: grid; grid-template-columns: repeat(auto-fill, minmax(260px, 1fr)); gap: 16px; }
.step { background: #fff; border-radius: 10px; overflow: hidden; box-shadow: 0 1px 3px rgba(0,0,0,.08); }
.step .cap { font-size: 13px; font-weight: 600; padding: 8px 12px; background: #fafafa; border-bottom: 1px solid #f0f0f0; }
.step .cap { font-size: 13px; font-weight: 600; padding: 8px 12px; background: #fafafa; border-bottom: 1px solid #f0f0f0; display:flex; align-items:center; gap:8px; }
.step .cap .badge { flex-shrink:0; display:inline-flex; align-items:center; justify-content:center; min-width:24px; height:24px; padding:0 6px; border-radius:6px; background:#2563eb; color:#fff; font-size:13px; font-weight:700; }
.step .cap .ttext { flex:1; }
.step .cap small { color: #999; font-weight: 400; display:block; margin-top:2px; }
.step .desc { font-size: 12px; line-height: 1.7; color: #4b5563; padding: 10px 12px; background: #f9fafb; border-bottom: 1px solid #f0f0f0; }
.step .desc b { color:#1f2937; }
.step img { width: 100%; display: block; background: #eee; cursor: zoom-in; }
.step .noimg { padding: 30px; text-align: center; color: #ccc; font-size: 13px; }
.big img { max-height: 520px; object-fit: contain; }
@@ -49,6 +53,7 @@
.lightbox { position: fixed; inset: 0; background: rgba(0,0,0,.85); display: none; align-items: center; justify-content: center; z-index: 50; cursor: zoom-out; }
.lightbox img { max-width: 95%; max-height: 95%; }
</style>
<script src="/static/img_downscale.js"></script>
</head>
<body>
<div class="container">
@@ -147,8 +152,8 @@
<div class="card">
<h2 style="margin-top:0">🎯 最终结果</h2>
<div class="steps" style="grid-template-columns: repeat(auto-fill, minmax(320px, 1fr))">
<div class="step big"><div class="cap">输入原图</div><img id="finalInput"></div>
<div class="step big"><div class="cap">最终结果</div><img id="finalOut"></div>
<div class="step big"><div class="cap"><span class="badge" style="background:#9ca3af">输入</span><span class="ttext">输入原图</span></div><img id="finalInput"></div>
<div class="step big"><div class="cap"><span class="badge"></span><span class="ttext">最终结果<small>接口11 最终输出 = ⑩接缝融合结果</small></span></div><img id="finalOut"></div>
</div>
</div>
@@ -192,19 +197,55 @@ function flog(msg, level) {
function clearLog() { FE_LOGS.length = 0; document.getElementById('logPanel').innerHTML = ''; }
const STEPS = [
{ key: 'baseline_overlay', title: '①-a 发际线分割线', sub: '黄线=baseline' },
{ key: 'upper_overlay', title: '①-b 上半区', sub: '青=baseline以上' },
{ key: 'hair_seg_overlay', title: '①-c 头发分割', sub: '绿=头发像素' },
{ key: 'top_fill_overlay', title: '①-d 填充到基线', sub: '蓝=top_fill(仅eroded/closed' },
{ key: 'closed_overlay', title: '①-e 闭合区域', sub: '紫=closed(仅eroded/closed' },
{ key: 'hairline_overlay', title: '①-f 头发内轮廓线', sub: '绿=头发内轮廓(额头弧+两侧到下颌),黄=baseline折线(仅pushed' },
{ key: 'pushed_overlay', title: '①-g 外推发际线', sub: '青=外推线(进头发push_cm),红=遮罩,绿=内轮廓(仅pushed' },
{ key: 'mask_overlay', title: '① 最终遮罩(叠加)', sub: '红=最终遮罩区' },
{ key: 'mask', title: '① 纯遮罩', sub: '白=贴回区' },
{ key: 'swap_raw', title: '② 生成全帧', sub: '换发型结果' },
{ key: 'hard_paste', title: '③ 严格贴回', sub: '遮罩内=生成,外=原图' },
{ key: 'alpha', title: '④ 融合权重', sub: '白=用生成图' },
{ key: 'final', title: '④ 接缝融合(最终)', sub: '最终输出' },
{ no: '①', key: 'baseline_overlay', title: '发际线分割线 baseline', sub: '黄线=baseline(眉峰水平连线)',
desc: '用 468 点人脸关键点定位两侧眉峰,连成一条水平线作为「上半区」的底界。'
+ '这条线把画面分成上下两半:以上是额头+头发(要处理),以下是五官(保持不动)。'
+ '它是后续所有遮罩、外推、贴回的坐标基准线。图中的黄线就是 baseline,红点为 151 号中心点(径向外推的圆心)。' },
{ no: '②', key: 'upper_overlay', title: '上半区 upper', sub: '青色=baseline 以上区域',
desc: '把 baseline 以上到画面顶部的整片区域标为「上半区」。后续的头发分割、发际线外推、'
+ '最终遮罩都只会在这个上半区内计算,确保下半张脸(眉、眼、鼻、嘴)永远不被改动。'
+ '青色覆盖的就是上半区范围。' },
{ no: '③', key: 'hair_seg_overlay', title: '头发分割', sub: '绿色=头发像素',
desc: '用语义分割模型(默认 SegFormer,可选 BiSeNet)逐像素判断哪些是「头发」。'
+ '绿色覆盖的就是被识别为头发的像素。这一步的目的是找到现有头发的边界,'
+ '为下一步「发际线内轮廓」提供输入——发际线就长在头发区域的内边缘上。' },
{ no: '④', key: 'hairline_overlay', title: '头发内轮廓线', sub: '绿=内轮廓(额头弧+两侧),黄=baseline',
desc: '从头发分割结果里提取出「头发的内轮廓」:即头发与皮肤交界的那条线。'
+ '它包含额头弧线(发际线本体)和两侧向下的鬓角轮廓。'
+ '提取方式 hairline_edge=column 时按逐列(竖向)找头发最低点连成线;=contour 时用形态学轮廓。'
+ '绿色折线就是提取出的内轮廓,黄色折线是 ① 的 baseline。这条内轮廓是外推发际线的起点。' },
{ no: '⑤', key: 'pushed_overlay', title: '外推发际线 + 遮罩', sub: '青=外推线,红=遮罩,绿=内轮廓,红点=圆心',
desc: '把 ④ 的发际线内轮廓「往头发方向(向头顶)推进 hairline_push_cm 厘米」得到一条新的外推线(青色)。'
+ '外推方式:以眉心(151 点)为圆心做径向外推,推过的这段就是「要新长出头发的区域」。'
+ '然后用【外推线(上界)到 baseline(下界)】之间的闭合区域作为最终遮罩(红色半透明)。'
+ 'push_cm 越大,新发际线越靠上、生发区越大(默认 0.8cm)。' },
{ no: '⑥', key: 'mask_overlay', title: '最终遮罩(叠加图)', sub: '红色=要重绘/贴回的区域',
desc: '把 ⑤ 算出的遮罩叠回原图看效果。红色区域 = 需要被新生成的头发覆盖的位置(遮罩内),'
+ '红色以外 = 保持原样不动(遮罩外)。这张图用来直观确认遮罩范围是否合理——'
+ '理想情况是红色正好覆盖额头该生发的区域,不越界到眉毛或脸颊。' },
{ no: '⑦', key: 'mask', title: '纯遮罩', sub: '白色=贴回区,黑色=保留区',
desc: '同一张遮罩的纯黑白版本(无原图背景)。白色=贴回区,黑色=保留区。'
+ '这张纯遮罩会作为 ext_mask 传给换发型服务,让 webui 精确地只在这个区域内重绘画头发。'
+ '它的好处是不受背景图干扰,便于检查遮罩形状是否干净(无噪点、无破洞)。' },
{ no: '⑧', key: 'swap_raw', title: '换发型生成', sub: 'change_hair 换该发际线类型后的整帧图',
desc: '调用 change_hair 换发型服务(POST :8801/api/swapHair/v1),传入原图 + 发际线类型 IDhairline_id)。'
+ '服务用对应发型的 LoRA 模型(webui img2imgdenoising_strength 控制生发强度)生成一张'
+ '「同一个人、换成该发际线类型发型」的完整图。注意:这张图是整帧都变了,'
+ '下一步会严格按遮罩只取额头那块,其余丢掉,保证五官不动。inpainting_fill/mask_blur 等参数控制这里的重绘方式。' },
{ no: '⑨', key: 'hard_paste', title: '严格贴回(无融合)', sub: '遮罩内=生成图,遮罩外=原图',
desc: '把 ⑧ 的生成图按 ⑥/⑦ 的遮罩「硬贴」回原图:遮罩内用生成图,遮罩外完全保留原图。'
+ '这是没有做任何接缝处理的版本,因此遮罩边缘通常能看到明显的接缝/色差。'
+ '它的作用是让你对比看出「融合前后的差别」——边缘接缝要靠下一步的融合来消除。' },
{ no: '⑩', key: 'alpha', title: '融合权重 alpha', sub: '白=用生成图,黑=保留原图,灰=过渡',
desc: '决定每个像素最终取多少比例的生成图。纯白(=1)完全用生成图,纯黑(=0)完全保留原图,'
+ '灰色是两者按比例过渡。blend_method=multiband/two_stage 时是多层金字塔权重(过渡带较宽、自然);'
+ '=feather/alpha_gradient 时是单层羽化(硬边缘软过渡)。这张图用来理解融合是怎么"渐变"地把新头发融进去的。' },
{ no: '⑪', key: 'final', title: '接缝融合(最终输出)', sub: '接口11 最终结果',
desc: '按 ⑩ 的权重,把生成图和原图加权融合,得到无接缝的最终图。这就是接口11 的最终返回结果。'
+ 'blend_method 选择融合算法:multiband=多频段金字塔(分频段融合,大色差场景用 two_stage 先泊松调色再多频段);'
+ 'seamless=泊松无缝克隆(梯度域自动调色);feather/alpha_gradient=简单羽化。'
+ 'color_match=true 时融合前还做一次 Reinhard 颜色迁移消除整体色差(seamless/two_stage 自带调色故跳过)。'
+ '本接口不含重绘,需要重绘(美颜/补发丝)见接口12。' },
];
function $(id) { return document.getElementById(id); }
@@ -212,13 +253,16 @@ function setStatus(text, type) { const b = $('statusBar'); b.textContent = text;
function pick(obj, name) { if (!obj) return null; return obj[name + '_url'] || obj[name + '_base64'] || null; }
function zoom(src) { $('lightboxImg').src = src; $('lightbox').style.display = 'flex'; }
function stepCard(title, sub, src) {
function stepCard(st, src) {
const div = document.createElement('div');
div.className = 'step';
const hasImg = src && src.length > 50;
const img = hasImg ? '<img src="' + src + '" onclick="zoom(this.src)">'
: '<div class="noimg">无图(后端返回空)</div>';
div.innerHTML = '<div class="cap">' + title + '<small>' + (sub||'') + (hasImg ? ' ('+src.length+'字符)' : '') + '</small></div>' + img;
const badge = st.no ? '<span class="badge">' + st.no + '</span>' : '';
const ttext = '<span class="ttext">' + (st.title||'') + '<small>' + (st.sub||'') + (hasImg ? ' ('+src.length+'字符)' : '') + '</small></span>';
const desc = st.desc ? '<div class="desc">' + st.desc + '</div>' : '';
div.innerHTML = '<div class="cap">' + badge + ttext + '</div>' + desc + img;
return div;
}
@@ -238,14 +282,15 @@ function renderResult(d) {
const src = pick(s, st.key);
const hasImg = src && src.length > 50;
flog(' 渲染 ' + st.key + ': ' + (hasImg ? '有图(' + src.length + '字符)' : '无图'), hasImg ? 'info' : 'warn');
grid.appendChild(stepCard(st.title, st.sub, src));
grid.appendChild(stepCard(st, src));
});
flog('renderResult 完成', 'info');
}
async function submitTest() {
const file = $('imageFile').files[0];
let file = $('imageFile').files[0];
if (!file) { setStatus('请先选择图片', 'error'); return; }
file = await window.downscaleImageFile(file);
// 页面隐藏但仍提交的固定默认值
const HIDDEN = {
seg_model: 'segformer',
@@ -364,6 +409,10 @@ async function downloadBackendLog() {
}
}
// 步骤序号 → 对应英文 key 的映射,供按序号定位步骤
const STEP_BY_NO = {};
STEPS.forEach(s => { if (s.no) STEP_BY_NO[s.no] = s.key; });
// 参数联动(遮罩/融合已固定,无下拉联动)
$('imageFile').addEventListener('change', function(){ if(this.files.length) flog('选择图片: ' + this.files[0].name, 'info'); });
+97 -34
View File
@@ -47,22 +47,29 @@
.log-panel .lvl-err { color: #f48771; }
.lightbox { position: fixed; inset: 0; background: rgba(0,0,0,.85); display: none; align-items: center; justify-content: center; z-index: 50; cursor: zoom-out; }
.lightbox img { max-width: 95%; max-height: 95%; }
.hidden { display: none; }
</style>
<script src="/static/img_downscale.js"></script>
</head>
<body>
<div class="container">
<h1>接口12 — 发际线带重绘 <span style="font-size:13px;color:#888">Flux-2 保色重绘)</span></h1>
<h1>接口12 — 发际线带重绘 <span style="font-size:13px;color:#888">final + 纯红遮罩 → ComfyUI 重绘)</span></h1>
<div class="subtitle">
内部先跑<b>接口11</b>拿到 ④接缝融合最终图(final),再取 <b>⑤-① 发际线重绘带</b>(发际线外推 band_lo_mult×push ~ band_hi_mult×push、经 baseline 截断只留上部)作遮罩,
<b>Flux-2ComfyUI</b> 保色重绘,重绘结果与 final 融合<br>
接口11 参数用于内部生成 final 与重绘带;<b>comfyui_prompt</b> 控制 Flux-2 提示词。⚠️ 需 ComfyUI(:8188) 在跑。
内部先跑<b>接口11</b>拿到 ④接缝融合最终图(final),再取 <b>⑤-① 发际线重绘带</b>(发际线外推 band_lo_mult×push ~ band_hi_mult×push、经 baseline 截断只留上部)生成
<b>纯红遮罩 PNG</b>(遮罩区=(255,0,0,255),其余全透明)<br>
前端拿到 final + 遮罩后,调 <b>后端重绘接口(/api/v1/redraw</b>完成重绘。⚠️ 需 ComfyUI(:8188) 在跑。
对照仅生成不重绘:<a href="/static/test_interface11_debug.html">接口11 调试页</a>
</div>
<div class="card">
<div class="upload-row">
<input type="file" id="imageFile" accept="image/*">
<button class="btn btn-primary" id="submitBtn" onclick="submitTest()">🎨 提交重绘</button>
<button class="btn btn-primary" id="submitBtn" onclick="submitTest()">🎨 生成 final+遮罩</button>
<button class="btn btn-green" id="redrawBtn" onclick="runLocalRedraw()" disabled>🧪 重绘</button>
</div>
<div class="upload-row" style="margin-top:10px">
<label style="font-size:13px;font-weight:600;white-space:nowrap">重绘提示词</label>
<input type="text" id="localTestPrompt" value="填充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜" style="flex:1;min-width:200px;padding:8px;border:1px solid #ddd;border-radius:8px">
</div>
<div class="upload-row" style="margin-top:10px">
<label style="font-size:13px;font-weight:600;white-space:nowrap">X-Internal-Token</label>
@@ -99,7 +106,7 @@
</div>
<div class="pf">
<label>color_match <span class="desc">融合前颜色迁移(消除色差)</span></label>
<div class="row"><input type="checkbox" id="colorMatch" checked style="width:18px;height:18px"><span class="desc">multiband/feather 生效;seamless/two_stage 自带调色</span></div>
<div class="row"><input type="checkbox" id="colorMatch" style="width:18px;height:18px"><span class="desc">multiband/feather 生效;seamless/two_stage 自带调色</span></div>
</div>
<div class="pf">
<label>color_match_strength <span class="desc">颜色迁移强度(0~1)</span></label>
@@ -119,23 +126,23 @@
</div>
</div>
<div class="pf" style="margin-top:14px">
<label>comfyui_prompt <span class="desc">Flux-2 提示词,留空=默认「补充遮罩区域的头发,加一点美颜」</span></label>
<textarea id="comfyuiPrompt" rows="2" style="width:100%;padding:8px;border:1px solid #ddd;border-radius:8px;font-size:13px;font-family:inherit;resize:vertical" placeholder="留空用默认提示词"></textarea>
<label>comfyui_prompt <span class="desc">已下线(后端不再做 Flux-2 重绘);重绘提示词改用上方「重绘提示词」输入框</span></label>
<textarea id="comfyuiPrompt" rows="2" style="width:100%;padding:8px;border:1px solid #ddd;border-radius:8px;font-size:13px;font-family:inherit;resize:vertical" placeholder="已下线,留空即可"></textarea>
</div>
<div style="font-size:12px;color:#888;margin-top:8px">遮罩固定 pushed,重绘固定 Flux-2隐藏参数(seg_model/hairline_edge/is_hr/edge_erode_px/mb_feather_px/transition_band_px/inpainting_fill/mask_blur/mask_dilate_scale)按默认值随请求提交。换发型走 GPU + Flux-2 重绘,单次约 15~30s</div>
<div style="font-size:12px;color:#888;margin-top:8px">遮罩固定 pushed;后端只产出 final+纯红遮罩(不做重绘)。隐藏参数(seg_model/hairline_edge/is_hr/edge_erode_px/mb_feather_px/transition_band_px/inpainting_fill/mask_blur/mask_dilate_scale)按默认值随请求提交。beauty_alpha/comfyui_prompt 已不再生效</div>
</div>
<div class="status hidden" id="statusBar"></div>
<div id="resultsArea" class="hidden">
<div class="card">
<h2 style="margin-top:0">🎯 两版重绘对比</h2>
<h2 style="margin-top:0">🎯 final + 纯红遮罩 → 重绘结果</h2>
<div class="steps" style="grid-template-columns: repeat(auto-fill, minmax(300px, 1fr))">
<div class="step big"><div class="cap">接口11 final <small>④ 接缝融合(重绘输入基底,无美颜)</small></div><img id="finalBase"></div>
<div class="step big"><div class="cap">A · 整帧重绘 <small>全脸美颜 + 全脸重绘(=手动 ComfyUI</small></div><img id="outFull"></div>
<div class="step big"><div class="cap">B · 局部加发+全脸美颜 <small>加发只在发际线带、美颜保留全脸</small></div><img id="outBand"></div>
<div class="step big"><div class="cap">⑤-① 发际线重绘带遮罩 <small>纯红 alpha PNG(遮罩区=红+不透明,其余全透明</small></div><img id="maskPng"></div>
<div class="step big"><div class="cap">🧪 重绘结果 <small>final + 遮罩 → ComfyUI(0716add-hair)</small></div><img id="localResult"></div>
</div>
<div style="font-size:12px;color:#888;margin-top:10px">对比要点:A 会重绘整张脸(五官/发型都可能变);B 只在发际线带加发、其余区域保留 final 结构并叠加全脸美颜(强度由 beauty_alpha 控制)</div>
<div style="font-size:12px;color:#888;margin-top:10px">流程:后端产出 final(接缝融合基底)+ 纯红遮罩 PNG,再调后端 /api/v1/redraw 完成发际线补发</div>
</div>
<div class="card">
@@ -180,10 +187,13 @@ const STEPS = [
{ key: 'input', title: '原图', sub: '接口输入' },
{ key: 'final', title: '接口11 ④ final', sub: '接缝融合最终图(重绘输入基底,无美颜)' },
{ key: 'redraw_band_overlay', title: '⑤-① 发际线重绘带', sub: '紫=lo×push↔hi×push之间、经 baseline 截断只留上部' },
{ key: 'redraw_full', title: 'A · 整帧重绘(Flux-2)', sub: '全脸美颜+全脸重绘(=手动 ComfyUI)' },
{ key: 'redraw_band', title: 'B · 局部加发+全脸美颜', sub: 'band内=ComfyUI加发;band外=final+beauty_alpha美颜' },
{ key: 'redraw_band_mask', title: '⑤-② 纯红遮罩 PNG', sub: '遮罩区=(255,0,0,255)、其余全透明;交给后端重绘' },
];
// 缓存最近一次后端返回的 final(JPG data URI)和纯红遮罩(PNG data URI),供重绘使用
let _finalDataUri = '';
let _maskDataUri = '';
function $(id) { return document.getElementById(id); }
function setStatus(text, type) { const b = $('statusBar'); b.textContent = text; b.className = 'status ' + type; }
function pick(obj, name) { if (!obj) return null; return obj[name + '_url'] || obj[name + '_base64'] || null; }
@@ -200,19 +210,20 @@ function stepCard(title, sub, src) {
}
function renderResult(d) {
flog('renderResult 开始 (blend=' + (d.blend_method || '?') + ', beauty_alpha=' + d.beauty_alpha + ')', 'info');
flog('renderResult 开始 (blend=' + (d.blend_method || '?') + ')', 'info');
const s = d.steps || {};
$('finalBase').src = pick(s, 'final') || '';
const finalSrc = pick(s, 'final') || '';
const maskSrc = pick(s, 'redraw_band_mask') || '';
_finalDataUri = finalSrc;
_maskDataUri = maskSrc;
$('finalBase').src = finalSrc;
$('finalBase').onclick = function(){ zoom(this.src); };
$('outFull').src = pick(s, 'redraw_full') || pick(s, 'redraw_c') || '';
$('outFull').onclick = function(){ zoom(this.src); };
$('outBand').src = pick(s, 'redraw_band') || '';
$('outBand').onclick = function(){ zoom(this.src); };
$('maskPng').src = maskSrc;
$('maskPng').onclick = function(){ zoom(this.src); };
const grid = $('stepsGrid'); grid.innerHTML = '';
$('stepsInfo').textContent = '(mask=pushed, blend=' + (d.blend_method || '?') + ', redraw=Flux-2, beauty_alpha=' + d.beauty_alpha + ')';
$('stepsInfo').textContent = '(mask=pushed, blend=' + (d.blend_method || '?') + ')';
if (d.redraw && d.redraw.enabled) {
flog('重绘带 band_pixels=' + d.redraw.band_pixels + ' push_px=' + d.redraw.push_px, 'info');
if (d.redraw.c_error) flog('Flux-2 重绘失败: ' + d.redraw.c_error, 'warn');
} else if (d.redraw && d.redraw.error) {
flog('重绘带计算失败: ' + d.redraw.error, 'warn');
}
@@ -222,12 +233,16 @@ function renderResult(d) {
flog(' 渲染 ' + st.key + ': ' + (hasImg ? '有图(' + src.length + '字符)' : '无图'), hasImg ? 'info' : 'warn');
grid.appendChild(stepCard(st.title, st.sub, src));
});
flog('renderResult 完成', 'info');
// final + 遮罩 都有 → 允许调后端重绘
const canRedraw = !!(finalSrc && maskSrc);
$('redrawBtn').disabled = !canRedraw;
flog('renderResult 完成 canRedraw=' + canRedraw, 'info');
}
async function submitTest() {
const file = $('imageFile').files[0];
let file = $('imageFile').files[0];
if (!file) { setStatus('请先选择图片', 'error'); return; }
file = await window.downscaleImageFile(file);
// 页面隐藏但仍提交的固定默认值
const HIDDEN = {
seg_model: 'segformer',
@@ -254,8 +269,8 @@ async function submitTest() {
flog('隐藏参数固定: ' + JSON.stringify(HIDDEN), 'info');
const btn = $('submitBtn');
btn.disabled = true; btn.textContent = '⏳ 重绘中...';
setStatus('正在请求(内部跑接口11,再 Flux-2 重绘,约 15~30s...', 'info');
btn.disabled = true; btn.textContent = '⏳ 生成中...';
setStatus('正在请求(内部跑接口11 生成 final + 纯红遮罩,约 10~15s...', 'info');
$('resultsArea').classList.remove('hidden');
const form = new FormData();
@@ -305,15 +320,15 @@ async function submitTest() {
if (json.code === 0) {
const d = json.data;
flog('后端返回 blend=' + d.blend_method + ' hairline_push_cm=' + d.hairline_push_cm + ' mask_pixels=' + d.mask_pixels, 'info');
flog('后端返回 comfyui_prompt=' + d.comfyui_prompt, 'info');
flog('后端 _rid=' + d._rid, 'info');
flog('后端返回 _rid=' + d._rid, 'info');
const s = d.steps || {};
Object.keys(s).filter(k => k.endsWith('_base64')).forEach(k => {
const len = s[k] ? s[k].length : 0;
flog(' steps.' + k + ' = ' + (len > 0 ? len + '字符' : '空'), len > 0 ? 'info' : 'warn');
});
const okRedraw = d.redraw && d.redraw.enabled && !d.redraw.c_error && (pick(s,'redraw_full'));
setStatus((okRedraw ? '✅ 重绘成功(A整帧 / B局部+美颜)' : '⚠️ 已返回(重绘可能未生效,见日志)') + ' (' + dt + 's) _rid=' + d._rid, okRedraw ? 'success' : 'error');
const hasFinal = !!(pick(s, 'final'));
const hasMask = !!(pick(s, 'redraw_band_mask'));
setStatus((hasFinal && hasMask ? '✅ 已生成 final + 纯红遮罩' : '⚠️ 已返回(final/遮罩缺失,见日志)') + ' (' + dt + 's) _rid=' + d._rid, (hasFinal && hasMask) ? 'success' : 'error');
renderResult(d);
} else {
setStatus('❌ 业务错误 code=' + json.code + '' + json.message, 'error');
@@ -323,7 +338,55 @@ async function submitTest() {
setStatus('❌ 网络错误: ' + err.message, 'error');
flog('网络错误: ' + err.message, 'error');
} finally {
btn.disabled = false; btn.textContent = '🎨 提交重绘';
btn.disabled = false; btn.textContent = '🎨 生成 final+遮罩';
}
}
// data URI → Blob,用于把后端返回的 final/遮罩图作为文件 POST 给后端重绘
function dataUriToBlob(dataUri) {
const [meta, b64] = dataUri.split(',');
const mime = (meta.match(/data:([^;]+)/) || [, 'application/octet-stream'])[1];
const bin = atob(b64);
const arr = new Uint8Array(bin.length);
for (let i = 0; i < bin.length; i++) arr[i] = bin.charCodeAt(i);
return new Blob([arr], { type: mime });
}
async function runLocalRedraw() {
if (!_finalDataUri || !_maskDataUri) { setStatus('缺少 final 或遮罩,请先生成', 'error'); return; }
const prompt = $('localTestPrompt').value.trim() || '填充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜';
const btn = $('redrawBtn');
btn.disabled = true; btn.textContent = '⏳ 重绘中...';
flog('===== 调后端重绘 =====', 'info');
flog('提示词=' + prompt, 'info');
const form = new FormData();
form.append('image_file', dataUriToBlob(_finalDataUri), 'final.jpg');
form.append('mask_file', dataUriToBlob(_maskDataUri), 'mask.png');
form.append('prompt', prompt);
const t0 = performance.now();
try {
flog('fetch POST ' + API_BASE + '/api/v1/redraw', 'info');
const resp = await fetch(API_BASE + '/api/v1/redraw', { method: 'POST', body: form });
flog('收到响应 http=' + resp.status, resp.ok ? 'info' : 'error');
const dt = ((performance.now() - t0) / 1000).toFixed(2);
const json = await resp.json();
if (json.code === 0 && json.data && json.data.image_base64) {
$('localResult').src = json.data.image_base64;
$('localResult').onclick = function(){ zoom(this.src); };
setStatus('✅ 重绘完成 (' + dt + 's)', 'success');
flog('重绘完成 耗时=' + dt + 's', 'info');
} else {
const msg = json.message || JSON.stringify(json);
setStatus('❌ 重绘失败:' + msg, 'error');
flog('重绘失败: ' + msg, 'error');
}
} catch (err) {
setStatus('❌ 重绘网络错误:' + err.message, 'error');
flog('重绘网络错误: ' + err.message, 'error');
} finally {
btn.disabled = false; btn.textContent = '🧪 重绘';
}
}
@@ -354,8 +417,8 @@ async function downloadBackendLog() {
$('imageFile').addEventListener('change', function(){ if(this.files.length) flog('选择图片: ' + this.files[0].name, 'info'); });
flog('接口12 重绘测试页加载完成(两版对比:A整帧 / B局部加发+全脸美颜', 'info');
flog('默认: hairline=chang_bolang, push=0.8, blend=two_stage, cm_strength=0.4, beauty_alpha=0.6;需 ComfyUI(:8188) 在跑', 'info');
flog('接口12 重绘测试页加载完成(后端产出 final+纯红遮罩 → 后端 /api/v1/redraw 重绘', 'info');
flog('默认: hairline=chang_bolang, push=0.8, blend=two_stage, cm_strength=0.4;需 ComfyUI(:8188) 在跑', 'info');
</script>
</body>
</html>
+77 -14
View File
@@ -37,20 +37,26 @@
.lightbox img { max-width: 95%; max-height: 95%; }
.hidden { display: none; }
</style>
<script src="/static/img_downscale.js"></script>
</head>
<body>
<div class="container">
<h1>接口12 final — 发际线带重绘 <span style="font-size:13px;color:#888">(精简版)</span></h1>
<h1>接口12 final — 发际线带重绘 <span style="font-size:13px;color:#888">(精简版final + 纯红遮罩 → ComfyUI 重绘</span></h1>
<div class="subtitle">
只需上传图片 + 选择发型,其余参数全部用当前调优默认值(<code>/api/v1/hairline/grow_v2_final</code>)。<br>
重绘输出为<b>整帧重绘</b>(全脸美颜 + 全脸重绘,=手动 ComfyUI)。⚠️ 需 ComfyUI(:8188) 在跑。
后端产出 <b>④ final(接缝融合基底)</b> + <b>⑤-② 纯红遮罩 PNG</b>,再调 <b>后端重绘接口(/api/v1/redraw</b>完成发际线带重绘。⚠️ 需 ComfyUI(:8188) 在跑。
局部加发版见 <a href="/static/test_interface12_final_v2.html">接口12 final v2</a>;完整参数调试见 <a href="/static/test_interface12.html">接口12 调试页</a>
</div>
<div class="card">
<div class="upload-row">
<input type="file" id="imageFile" accept="image/*">
<button class="btn btn-primary" id="submitBtn" onclick="submitTest()">🎨 提交重绘</button>
<button class="btn btn-primary" id="submitBtn" onclick="submitTest()">🎨 生成 final+遮罩</button>
<button class="btn btn-green" id="redrawBtn" onclick="runLocalRedraw()" disabled>🧪 重绘</button>
</div>
<div class="upload-row" style="margin-top:10px">
<label style="font-size:13px;font-weight:600;white-space:nowrap">重绘提示词</label>
<input type="text" id="localTestPrompt" value="填充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜" style="flex:1;min-width:200px;padding:8px;border:1px solid #ddd;border-radius:8px">
</div>
<div class="params">
<div class="pf">
@@ -70,11 +76,13 @@
<div id="resultsArea" class="hidden">
<div class="card">
<h2 style="margin-top:0">🎯 整帧重绘结果</h2>
<h2 style="margin-top:0">🎯 final + 纯红遮罩 → 重绘结果</h2>
<div class="steps" style="grid-template-columns: repeat(auto-fill, minmax(300px, 1fr))">
<div class="step big"><div class="cap">接口11 final <small>④ 接缝融合(重绘输入基底,无美颜)</small></div><img id="finalBase"></div>
<div class="step big"><div class="cap">整帧重绘 <small>全脸美颜 + 全脸重绘(=手动 ComfyUI</small></div><img id="outFull"></div>
<div class="step big"><div class="cap">⑤-① 发际线重绘带遮罩 <small>纯红 alpha PNG(遮罩区=红+不透明,其余全透明</small></div><img id="maskPng"></div>
<div class="step big"><div class="cap">🧪 重绘结果 <small>final + 遮罩 → ComfyUI(0716add-hair)</small></div><img id="localResult"></div>
</div>
<div style="font-size:12px;color:#888;margin-top:10px">流程:后端产出 final(接缝融合基底)+ 纯红遮罩 PNG,再调后端 /api/v1/redraw 完成发际线补发。</div>
</div>
</div>
</div>
@@ -86,6 +94,10 @@ const API_BASE = window.location.origin;
const ENDPOINT = '/api/v1/hairline/grow_v2_final';
const TOKEN = 'dev-shared-secret-2026';
// 缓存最近一次后端返回的 final(data URI)和纯红遮罩(data URI),供重绘使用
let _finalDataUri = '';
let _maskDataUri = '';
function $(id) { return document.getElementById(id); }
function setStatus(text, type) { const b = $('statusBar'); b.textContent = text; b.className = 'status ' + type; }
function pick(obj, name) { if (!obj) return null; return obj[name + '_url'] || obj[name + '_base64'] || null; }
@@ -93,19 +105,36 @@ function zoom(src) { $('lightboxImg').src = src; $('lightbox').style.display = '
function renderResult(d) {
const s = d.steps || {};
$('finalBase').src = pick(s, 'final') || '';
const finalSrc = pick(s, 'final') || '';
const maskSrc = pick(s, 'redraw_band_mask') || '';
_finalDataUri = finalSrc;
_maskDataUri = maskSrc;
$('finalBase').src = finalSrc;
$('finalBase').onclick = function(){ zoom(this.src); };
$('outFull').src = pick(s, 'redraw_full') || pick(s, 'redraw_c') || '';
$('outFull').onclick = function(){ zoom(this.src); };
$('maskPng').src = maskSrc;
$('maskPng').onclick = function(){ zoom(this.src); };
const canRedraw = !!(finalSrc && maskSrc);
$('redrawBtn').disabled = !canRedraw;
}
// data URI → Blob,用于把后端返回的 final/遮罩图作为文件 POST 给后端重绘
function dataUriToBlob(dataUri) {
const [meta, b64] = dataUri.split(',');
const mime = (meta.match(/data:([^;]+)/) || [, 'application/octet-stream'])[1];
const bin = atob(b64);
const arr = new Uint8Array(bin.length);
for (let i = 0; i < bin.length; i++) arr[i] = bin.charCodeAt(i);
return new Blob([arr], { type: mime });
}
async function submitTest() {
const file = $('imageFile').files[0];
let file = $('imageFile').files[0];
if (!file) { setStatus('请先选择图片', 'error'); return; }
file = await window.downscaleImageFile(file);
const btn = $('submitBtn');
btn.disabled = true; btn.textContent = '⏳ 重绘中...';
setStatus('正在请求(内部跑接口11,再 Flux-2 重绘,约 15~30s...', 'info');
btn.disabled = true; btn.textContent = '⏳ 生成中...';
setStatus('正在请求(内部跑接口11 生成 final + 纯红遮罩,约 10~15s...', 'info');
$('resultsArea').classList.remove('hidden');
const form = new FormData();
@@ -124,8 +153,9 @@ async function submitTest() {
if (json.code === 0) {
const d = json.data;
const okRedraw = d.redraw && d.redraw.enabled && !d.redraw.c_error && pick(d.steps, 'redraw_full');
setStatus((okRedraw ? '✅ 整帧重绘成功' : '⚠️ 已返回(重绘可能未生效)') + ' (' + dt + 's)', okRedraw ? 'success' : 'error');
const hasFinal = !!(pick(d.steps, 'final'));
const hasMask = !!(pick(d.steps, 'redraw_band_mask'));
setStatus((hasFinal && hasMask ? '✅ 已生成 final + 纯红遮罩' : '⚠️ 已返回(final/遮罩缺失,见日志)') + ' (' + dt + 's)', (hasFinal && hasMask) ? 'success' : 'error');
renderResult(d);
} else {
setStatus('❌ 业务错误 code=' + json.code + '' + json.message, 'error');
@@ -133,7 +163,40 @@ async function submitTest() {
} catch (err) {
setStatus('❌ 网络错误: ' + err.message, 'error');
} finally {
btn.disabled = false; btn.textContent = '🎨 提交重绘';
btn.disabled = false; btn.textContent = '🎨 生成 final+遮罩';
}
}
async function runLocalRedraw() {
if (!_finalDataUri || !_maskDataUri) { setStatus('缺少 final 或遮罩,请先生成', 'error'); return; }
const prompt = $('localTestPrompt').value.trim() || '填充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜';
const btn = $('redrawBtn');
btn.disabled = true; btn.textContent = '⏳ 重绘中...';
const form = new FormData();
form.append('image_file', dataUriToBlob(_finalDataUri), 'final.jpg');
form.append('mask_file', dataUriToBlob(_maskDataUri), 'mask.png');
form.append('prompt', prompt);
const t0 = performance.now();
try {
const resp = await fetch(API_BASE + '/api/v1/redraw', {
method: 'POST',
body: form,
});
const dt = ((performance.now() - t0) / 1000).toFixed(2);
const json = await resp.json();
if (json.code === 0 && json.data && json.data.image_base64) {
$('localResult').src = json.data.image_base64;
$('localResult').onclick = function(){ zoom(this.src); };
setStatus('✅ 重绘完成 (' + dt + 's)', 'success');
} else {
setStatus('❌ 重绘失败:' + (json.message || JSON.stringify(json)), 'error');
}
} catch (err) {
setStatus('❌ 重绘网络错误:' + err.message, 'error');
} finally {
btn.disabled = false; btn.textContent = '🧪 重绘';
}
}
</script>
+3 -1
View File
@@ -37,6 +37,7 @@
.lightbox img { max-width: 95%; max-height: 95%; }
.hidden { display: none; }
</style>
<script src="/static/img_downscale.js"></script>
</head>
<body>
<div class="container">
@@ -100,8 +101,9 @@ function renderResult(d) {
}
async function submitTest() {
const file = $('imageFile').files[0];
let file = $('imageFile').files[0];
if (!file) { setStatus('请先选择图片', 'error'); return; }
file = await window.downscaleImageFile(file);
const btn = $('submitBtn');
btn.disabled = true; btn.textContent = '⏳ 重绘中...';
+8 -7
View File
@@ -69,6 +69,7 @@
.hidden { display: none !important; }
</style>
<script src="/static/img_downscale.js?v=2"></script>
</head>
<body>
<div class="container">
@@ -106,7 +107,7 @@
<div class="hint">JPG/PNG &nbsp;|&nbsp; 生发图生成较慢(数十秒~数分钟),请耐心等待</div>
<div style="margin-top:10px;display:flex;align-items:center;gap:8px">
<label style="font-size:13px;font-weight:600;color:#374151;white-space:nowrap">💬 提示词</label>
<input type="text" id="promptInput" value="充遮罩区域的头发,加一点美颜" style="flex:1;padding:8px 12px;border:1px solid #d1d5db;border-radius:6px;font-size:13px;max-width:500px">
<input type="text" id="promptInput" value="充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜" style="flex:1;padding:8px 12px;border:1px solid #d1d5db;border-radius:6px;font-size:13px;max-width:500px">
</div>
<div id="statusBar" class="status hidden"></div>
</div>
@@ -140,9 +141,9 @@ function $(id) { return document.getElementById(id); }
function setStatus(t, type) { const b=$('statusBar'); b.textContent=t; b.className='status '+type; }
async function submitTest() {
const f = $('imageFile').files[0];
let f = $('imageFile').files[0];
if (!f) { setStatus('请选择图片', 'error'); return; }
f = await window.downscaleImageFile(f);
_origUrl = URL.createObjectURL(f);
$('submitBtn').disabled = true; $('submitBtn').textContent = '⏳ 请求中...';
@@ -179,9 +180,9 @@ function renderSchemes(results) {
let html = '';
results.forEach((r, i) => {
const lb = TYPE_LABELS[r.hairline_type] || r.hairline_type;
// 直连 worker 时后端返回 base64网关才会改写为 *_url),URL 缺失则回退 data URI
const overlaySrc = r.image_url || (r.image_base64 ? 'data:image/png;base64,' + r.image_base64 : '');
const grownSrc = r.grown_image_url || (r.grown_image_base64 ? 'data:image/jpeg;base64,' + r.grown_image_base64 : '');
// 兼容网关 *_url 与 worker *_base64原始或 data URI
const overlaySrc = resolveImgSrc(r.image_url, r.image_base64, 'image/png');
const grownSrc = resolveImgSrc(r.grown_image_url, r.grown_image_base64, 'image/jpeg');
// 原图
const origSlot = '<div class="img-slot">'+
@@ -205,7 +206,7 @@ function renderSchemes(results) {
} else {
grownSlot = '<div class="img-slot">'+
'<div class="label"><span class="dot grown"></span>生发效果</div>'+
'<div class="na">⚠ 未返回<br><span style="font-size:10px;color:#9ca3af">ComfyUI 未就绪或生成失败</span></div></div>';
'<div class="na">⚠ 未返回<br><span style="font-size:10px;color:#9ca3af">生发失败(female=换发型/重绘,male=ComfyUI</span></div></div>';
}
html += '<div class="scheme-card">'+
+6 -5
View File
@@ -71,6 +71,7 @@
@media (max-width: 800px) { .results-layout, .preview-row { flex-direction: column; } }
</style>
<script src="/static/img_downscale.js?v=2"></script>
</head>
<body>
<div class="container">
@@ -93,7 +94,7 @@
</div>
<div class="upload-group" style="margin-top:14px">
<div class="label">💬 提示词(prompt</div>
<input type="text" id="promptInput" value="充遮罩区域的头发,加一点美颜" style="width:100%;padding:8px 12px;border:1px solid #d1d5db;border-radius:8px;font-size:14px;max-width:500px">
<input type="text" id="promptInput" value="充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜" style="width:100%;padding:8px 12px;border:1px solid #d1d5db;border-radius:8px;font-size:14px;max-width:500px">
</div>
<div style="margin-top:14px;display:flex;gap:12px;align-items:center">
<button class="btn btn-primary" id="submitBtn" onclick="submitTest()">🚀 提交</button>
@@ -139,9 +140,9 @@ function $(id) { return document.getElementById(id); }
function setStatus(t, type) { const b=$('statusBar'); b.textContent=t; b.className='status '+type; }
async function submitTest() {
const mf = $('markedFile').files[0];
let mf = $('markedFile').files[0];
if (!mf) { setStatus('请选择划线图', 'error'); return; }
mf = await window.downscaleImageFile(mf);
const markedUrl = URL.createObjectURL(mf);
// 先显示原图
@@ -161,7 +162,7 @@ async function submitTest() {
const _reqStart = performance.now();
try {
const r = await fetch(API_BASE + '/api/v1/hair/grow-b', { method:'POST', body:fd });
const r = await fetch(API_BASE + '/api/v1/hair/grow-b', { method:'POST', headers: { 'X-Internal-Token': 'dev-shared-secret-2026' }, body:fd });
const json = await r.json();
const _elapsed = ((performance.now() - _reqStart) / 1000).toFixed(2);
$('jsonContent').textContent = JSON.stringify(json, null, 2);
@@ -174,7 +175,7 @@ async function submitTest() {
$('hairlineType').style.display = 'inline-block';
}
const grownSrc = d.hair_growth_image_url || d.hair_growth_image_base64;
const grownSrc = resolveImgSrc(d.hair_growth_image_url, d.hair_growth_image_base64, 'image/jpeg');
if (grownSrc) {
$('blendTop').src = grownSrc;
$('blendTop').style.display = 'block';
+4 -2
View File
@@ -57,6 +57,7 @@
@media (max-width: 800px) { .results-layout { flex-direction: column; } }
</style>
<script src="/static/img_downscale.js"></script>
</head>
<body>
<div class="container">
@@ -121,8 +122,9 @@ function $(id) { return document.getElementById(id); }
function setStatus(t, type) { const b=$('statusBar'); b.textContent=t; b.className='status '+type; }
async function submitTest() {
const f = $('imageFile').files[0];
let f = $('imageFile').files[0];
if (!f) { setStatus('请选择图片', 'error'); return; }
f = await window.downscaleImageFile(f);
$('imgPreview').innerHTML = '<img src="'+URL.createObjectURL(f)+'" alt="preview">';
$('submitBtn').disabled = true; $('submitBtn').textContent = '⏳ 分析中...';
@@ -131,7 +133,7 @@ async function submitTest() {
const fd = new FormData(); fd.append('image_file', f);
const _reqStart = performance.now();
try {
const r = await fetch(API_BASE + '/api/v1/face/features', { method:'POST', body:fd });
const r = await fetch(API_BASE + '/api/v1/face/features', { method:'POST', headers: { 'X-Internal-Token': 'dev-shared-secret-2026' }, body:fd });
const json = await r.json();
const _elapsed = ((performance.now() - _reqStart) / 1000).toFixed(2);
$('jsonContent').textContent = JSON.stringify(json, null, 2);
+26 -13
View File
@@ -88,6 +88,7 @@
.hidden { display: none !important; }
@media (max-width: 800px) { .results-layout { flex-direction: column; } }
</style>
<script src="/static/img_downscale.js?v=2"></script>
</head>
<body>
<div class="container">
@@ -112,6 +113,12 @@
</div>
</div>
</div>
<div class="form-group">
<label>生发效果图</label>
<label class="checkbox-inline" style="font-weight:normal;display:flex;align-items:center;gap:6px">
<input type="checkbox" id="genGrowImg" checked> generate_grow_image(默认开;关闭后跳过最耗时的生发,仅返回三档叠图与中心点)
</label>
</div>
<button class="btn btn-primary" id="submitBtn" onclick="submitTest()">🚀 提交</button>
<button class="btn btn-outline btn-sm" onclick="clearResults()">清除</button>
</div>
@@ -195,19 +202,20 @@ function selectAllHair(select) {
}
async function submitTest() {
const f = $('imageFile').files[0];
let f = $('imageFile').files[0];
if (!f) { setStatus('请选择图片', 'error'); return; }
const checked = [...document.querySelectorAll('#hairStyleGroup input:checked')].map(cb => cb.value);
if (!checked.length) { setStatus('请至少选择一个发型', 'error'); return; }
f = await window.downscaleImageFile(f);
_origUrl = URL.createObjectURL(f);
$('submitBtn').disabled = true; $('submitBtn').textContent = '⏳ ...';
setStatus('请求中...', 'info'); $('resultsArea').classList.add('hidden');
const fd = new FormData(); fd.append('image_file', f); fd.append('gender', $('gender').value); fd.append('hair_style', checked.join(','));
const fd = new FormData(); fd.append('image_file', f); fd.append('gender', $('gender').value); fd.append('hair_style', checked.join(',')); fd.append('generate_grow_image', $('genGrowImg').checked ? 'true' : 'false');
const _reqStart = performance.now();
try {
const r = await fetch(API_BASE + '/api/v1/hairline/generate', { method:'POST', body:fd });
const r = await fetch(API_BASE + '/api/v1/hairline/generate', { method:'POST', headers: { 'X-Internal-Token': 'dev-shared-secret-2026' }, body:fd });
const json = await r.json();
const _elapsed = ((performance.now() - _reqStart) / 1000).toFixed(2);
$('jsonContent').textContent = JSON.stringify(json, null, 2);
@@ -235,25 +243,30 @@ async function submitTest() {
function renderGrid() {
if (!_images.length) { $('resultsGrid').innerHTML = '<span style="color:#9ca3af">无数据</span>'; return; }
let h = '';
// 叠图档:原图打底 + 透明 PNG 叠加(无原图或无叠图 → 显示占位)
const overlayCell = (label, url) => (url && _origUrl)
// 叠图档:原图打底 + 透明 PNG 图层(无原图或无叠图 → 显示占位)
const overlayCell = (label, src) => (src && _origUrl)
? '<div class="level-cell"><div class="level-label">'+label+'</div><div class="img-stack">'+
'<img class="layer-base" src="'+_origUrl+'" alt="原图">'+
'<img class="layer-anno" src="'+url+'" alt="'+label+'"></div></div>'
'<img class="layer-anno" src="'+src+'" alt="'+label+'"></div></div>'
: '<div class="level-cell"><div class="level-label">'+label+'</div><div class="level-none"></div></div>';
// 生发图:独立 img(已是 ComfyUI 完整人像照片)
const grownCell = (label, url) => url
? '<div class="level-cell"><div class="level-label">'+label+'</div><img src="'+url+'" alt="'+label+'"></div>'
const grownCell = (label, src) => src
? '<div class="level-cell"><div class="level-label">'+label+'</div><img src="'+src+'" alt="'+label+'"></div>'
: '<div class="level-cell"><div class="level-label">'+label+'</div><div class="level-none"></div></div>';
_images.forEach(function(it) {
// 兼容网关 *_url 与 worker *_base64
const mid = resolveImgSrc(it.image_middle_url, it.image_middle_base64, 'image/png');
const high = resolveImgSrc(it.image_high_url, it.image_high_base64, 'image/png');
const low = resolveImgSrc(it.image_low_url, it.image_low_base64, 'image/png');
const grown = resolveImgSrc(it.grown_image_url, it.grown_image_base64, 'image/jpeg');
h += '<div class="hair-block">' +
'<div class="hair-block-title">#' + (it.order||'—') + ' ' + (it.hairline_type||'') +
(it.grown_image_url ? ' &nbsp;<span style="font-size:11px;color:#7c3aed">含生发图</span>' : '') + '</div>' +
(grown ? ' &nbsp;<span style="font-size:11px;color:#7c3aed">含生发图</span>' : '') + '</div>' +
'<div class="level-row">' +
overlayCell('middle', it.image_middle_url) +
overlayCell('high', it.image_high_url) +
overlayCell('low', it.image_low_url) +
grownCell('生发图', it.grown_image_url) +
overlayCell('middle', mid) +
overlayCell('high', high) +
overlayCell('low', low) +
grownCell('生发图', grown) +
'</div>' +
'</div>';
});
+12 -3
View File
@@ -59,6 +59,7 @@
.diff-list { font-size: 12px; color: #6b7280; margin-top: 6px; line-height: 1.7; }
.diff-list li { margin-left: 18px; }
</style>
<script src="/static/img_downscale.js?v=2"></script>
</head>
<body>
<div class="container">
@@ -129,8 +130,9 @@ function setStatus(text, type) {
async function submitTest() {
const fileInput = $('imageFile');
const file = fileInput.files[0];
let file = fileInput.files[0];
if (!file) { setStatus('请先选择一张图片', 'error'); return; }
file = await window.downscaleImageFile(file);
const _reqStart = performance.now();
@@ -150,7 +152,7 @@ async function submitTest() {
form.append('image_file', file);
try {
const resp = await fetch(API_BASE + '/api/v1/face/measure-v2', { method: 'POST', body: form });
const resp = await fetch(API_BASE + '/api/v1/face/measure-v2', { method: 'POST', headers: { 'X-Internal-Token': 'dev-shared-secret-2026' }, body: form });
const json = await resp.json();
const _elapsed = ((performance.now() - _reqStart) / 1000).toFixed(2);
@@ -159,7 +161,10 @@ async function submitTest() {
if (json.code === 0) {
setStatus('✅ 请求成功 (' + _elapsed + 's) — request_id: ' + json.request_id, 'success');
showOverlay(json.data.annotated_image_url);
// 兼容本地直连 worker*_base64)与网关(*_url
const _d = json.data || {};
const annoUrl = resolveImgSrc(_d.annotated_image_url, _d.annotated_image_base64, 'image/png');
showOverlay(annoUrl);
renderMetrics(json.data);
$('metricsBar').classList.remove('hidden');
} else {
@@ -183,6 +188,10 @@ function showOverlay(annoUrl) {
setTimeout(() => showOverlay(annoUrl), 200);
return;
}
if (!annoUrl) {
$('imgPanel').innerHTML = '<span class="placeholder">后端未返回标注图(annotated_image_base64 为空)</span>';
return;
}
const checked = $('showAnno').checked ? '' : 'display:none';
const opacity = ($('annoOpacity').value / 100).toFixed(2);
+5 -4
View File
@@ -66,6 +66,7 @@
.badge-v2 { background: #7c3aed; color: #fff; font-size: 11px; padding: 2px 8px; border-radius: 10px; margin-left: 6px; vertical-align: middle; }
</style>
<script src="/static/img_downscale.js"></script>
</head>
<body>
<div class="container">
@@ -103,7 +104,7 @@
<div class="hint">JPG/PNG &nbsp;|&nbsp; 生发图生成较慢(数十秒~数分钟),请耐心等待 &nbsp;|&nbsp; 工作流: add_hair2.json</div>
<div style="margin-top:10px;display:flex;align-items:center;gap:8px">
<label style="font-size:13px;font-weight:600;color:#374151;white-space:nowrap">💬 提示词</label>
<input type="text" id="promptInput" value="充遮罩区域的头发,加一点美颜" style="flex:1;padding:8px 12px;border:1px solid #d1d5db;border-radius:6px;font-size:13px;max-width:500px">
<input type="text" id="promptInput" value="充遮罩区域的头发,皮肤加一点磨皮,再加一点美颜" style="flex:1;padding:8px 12px;border:1px solid #d1d5db;border-radius:6px;font-size:13px;max-width:500px">
</div>
<div id="statusBar" class="status hidden"></div>
</div>
@@ -137,9 +138,9 @@ function $(id) { return document.getElementById(id); }
function setStatus(t, type) { const b=$('statusBar'); b.textContent=t; b.className='status '+type; }
async function submitTest() {
const f = $('imageFile').files[0];
let f = $('imageFile').files[0];
if (!f) { setStatus('请选择图片', 'error'); return; }
f = await window.downscaleImageFile(f);
_origUrl = URL.createObjectURL(f);
$('submitBtn').disabled = true; $('submitBtn').textContent = '⏳ 请求中...';
@@ -153,7 +154,7 @@ async function submitTest() {
fd.append('prompt', $('promptInput').value);
const _reqStart = performance.now();
try {
const r = await fetch(API_BASE + '/api/v1/hair/grow-v2', { method:'POST', body:fd });
const r = await fetch(API_BASE + '/api/v1/hair/grow-v2', { method:'POST', headers: { 'X-Internal-Token': 'dev-shared-secret-2026' }, body:fd });
const json = await r.json();
const _elapsed = ((performance.now() - _reqStart) / 1000).toFixed(2);
$('jsonContent').textContent = JSON.stringify(json, null, 2);
+4 -2
View File
@@ -51,6 +51,7 @@
.lightbox { position: fixed; inset: 0; background: rgba(0,0,0,.85); display: none; align-items: center; justify-content: center; z-index: 50; cursor: zoom-out; }
.lightbox img { max-width: 95%; max-height: 95%; }
</style>
<script src="/static/img_downscale.js"></script>
</head>
<body>
<div class="container">
@@ -194,8 +195,9 @@ function renderMetrics(data) {
}
async function submitTest() {
const file = $('imageFile').files[0];
let file = $('imageFile').files[0];
if (!file) { setStatus('请先选择一张图片', 'error'); return; }
file = await window.downscaleImageFile(file);
const t0 = performance.now();
const btn = $('submitBtn');
@@ -208,7 +210,7 @@ async function submitTest() {
form.append('erode_cm', $('erodeCm').value || '1.2');
try {
const resp = await fetch(API_BASE + ENDPOINT, { method: 'POST', body: form });
const resp = await fetch(API_BASE + ENDPOINT, { method: 'POST', headers: { 'X-Internal-Token': 'dev-shared-secret-2026' }, body: form });
const json = await resp.json();
const dt = ((performance.now() - t0) / 1000).toFixed(2);
+38
View File
@@ -62,3 +62,41 @@ def test_threshold_gating_rejects_when_zeroed():
def test_pose_none_is_not_blocked():
"""solvePnP 失败(返回 None)时不拦截,check_frontal_face 返回 True。"""
assert pose.estimate_head_pose.__doc__ # 占位,确保导入
def test_iterative_flipped_solution_falls_back_to_sqpnp():
"""回归:部分正面照上 ITERATIVE 会解出 tz<0、roll≈±180°,应回退 SQPNP。
像素点取自一张真实正面短发照720×945裸跑 ITERATIVE 会得到负深度
"""
W, H = 720, 945
# 鼻尖 / 下巴 / 左眼外 / 右眼外 / 左嘴角 / 右嘴角(像素)
px = [
(358.32715988, 600.98652095),
(346.83344364, 779.63507116),
(242.94779778, 466.76155195),
(478.43703747, 480.10321766),
(284.13277388, 679.95527387),
(422.19510555, 684.31899190),
]
lm = [_LM(0.5, 0.5) for _ in range(478)]
for idx, (u, v) in zip(PNP_INDICES, px):
lm[idx] = _LM(u / W, v / H)
class _Holder:
landmark = lm
holder = _Holder()
# 确认裸 ITERATIVE 确实是翻转解(否则本回归失去意义)
image_points = np.array(px, dtype=np.float64)
cam = np.array([[float(W), 0, W / 2], [0, float(W), H / 2], [0, 0, 1]],
dtype=np.float64)
ok, rvec, tvec = cv2.solvePnP(
_MODEL_POINTS, image_points, cam, np.zeros((4, 1)),
flags=cv2.SOLVEPNP_ITERATIVE,
)
assert ok and float(tvec[2, 0]) < 0
yaw, pitch, roll = estimate_head_pose(holder, W, H)
assert abs(roll) < 30, f"roll 应被纠正,实际 roll={roll}"
assert check_frontal_face(holder, W, H) is True