xsl
443cfa298f
包含： - hair_service_sd: 主服务（换发型/换发色/生发，端口8801） - photo_service: LoRA调度+训练（端口32678） - hair_grow_service: 调试测试页（端口8888，含4个测试页） - 批量训练脚本（batch_train_hairstyles.py） - 发际线mask自动识别（hairline_mask.py，4种方案） - 手绘mask换发型（hair_swap_manual.py） - 文档：README.md + LARGE_FILES.md + docs/ 大文件（模型权重200G、训练数据123G）已排除，见 LARGE_FILES.md OSS/COS密钥已脱敏为环境变量，原文件备份在本地
426 lines
22 KiB
Python
426 lines
22 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""换发型（手绘mask重绘版）
|
||
|
||
与 hair_swap_debug.py 工作流完全一致，唯一区别在步骤③：
|
||
- debug版：重绘区域 = 原头发mask ∪ 新发型mask（自动计算）
|
||
- 本版： 重绘区域 = 用户手绘mask（白色=重绘，黑色=保留原图）
|
||
|
||
用户在页面上画哪里，SD 就重绘哪里，完全由用户控制重绘范围。
|
||
工作流：输入 → 粗推理 → 手绘mask → warpAffine → SD推理 → 贴回 → 消除接缝
|
||
"""
|
||
import os
|
||
import json
|
||
import glob
|
||
import time
|
||
import shutil
|
||
import base64
|
||
|
||
import cv2
|
||
import numpy as np
|
||
|
||
from gen_super_image import webui_img2img
|
||
from common.logger import config
|
||
from utils.landmark_processor import high_quality_warpAffine
|
||
from utils.landmark_processor import pts_1k_to_137
|
||
|
||
|
||
def hair_swap_manual(origin_img, hand_mask, hair_id, hairstyle_process, landmark_processor,
|
||
task_id,
|
||
# ===== 流程开关（真正生效）=====
|
||
strict_mask=False, # 步骤⑥ 严格按mask贴回
|
||
seamless_blend=True, # 步骤⑦ 泊松融合消除接缝
|
||
# ===== 尺寸/对齐（真正生效）=====
|
||
is_hr=True, # 高清(1152x1536) vs 标清(576x768)
|
||
dilate_kernel=(6, 18), # 步骤④ mask膨胀核 (x,y)
|
||
# ===== SD 推理（仅 denoising 可调，其余webui端固定）=====
|
||
denoising_strength=0.6, # 重绘强度（唯一能透传到webui的SD参数）
|
||
# ===== 贴回/融合（真正生效）=====
|
||
blend_dilate=(5, 5), # 步骤⑥ strict mask贴回时mask膨胀核
|
||
feather_px=0, # ★ strict贴回边缘羽化像素（0=无羽化硬边缘，>0=高斯模糊边缘）
|
||
seamless_dilate=(9, 9), # 步骤⑦ 泊松融合mask膨胀核
|
||
# ===== enhance 二次增强重绘 =====
|
||
enhance=False, # 步骤⑧ 是否对结果再做一次低强度SD重绘（让发丝更清晰）
|
||
enhance_denoising=0.35, # enhance 重绘强度（默认0.35，越低越保留原图）
|
||
):
|
||
"""手绘mask版换发型。
|
||
|
||
参数:
|
||
hand_mask: 用户手绘mask，灰度ndarray，白色(255)=重绘区，与 origin_img 同尺寸
|
||
其余参数同 hair_swap_debug
|
||
返回:
|
||
result_img: 最终结果图 BGR
|
||
steps: [{title, desc, images:[{label, b64}]}]
|
||
params_used: 实际使用的参数（回显）
|
||
"""
|
||
start_all = time.time()
|
||
steps = []
|
||
|
||
hairstyle_dir = config.get('default', 'hairstyleDir')
|
||
user_dir = config.get('default', 'userDir')
|
||
train_dir = config.get('default', 'train_dir')
|
||
userInfo_dir = config.get('default', 'userInfo_dir')
|
||
|
||
hair_material_dir = os.path.join(train_dir, hair_id)
|
||
material_save_path = os.path.join(hairstyle_dir, hair_id)
|
||
ref_img_path = os.path.join(material_save_path, "ref_rgb_8uc3_768.png")
|
||
if not os.path.exists(ref_img_path):
|
||
raise FileNotFoundError(f"发型材质不存在: {ref_img_path}")
|
||
|
||
user_img_name = f"swapdbg_{task_id}.jpg"
|
||
new_user_img_path = os.path.join(user_dir, user_img_name)
|
||
if os.path.exists(new_user_img_path):
|
||
os.remove(new_user_img_path)
|
||
cv2.imwrite(new_user_img_path, origin_img)
|
||
origin_img = cv2.imread(new_user_img_path)
|
||
|
||
ref_img = cv2.imread(ref_img_path)
|
||
|
||
# === 步骤1: 输入 ===
|
||
steps.append({
|
||
"title": "① 输入",
|
||
"desc": "用户人像 + 目标发型参考图。参考图来自训练材质 ref_rgb_8uc3_768.png",
|
||
"images": [
|
||
{"label": "用户原图", "b64": _enc(origin_img)},
|
||
{"label": f"发型参考图({hair_id})", "b64": _enc(cv2.resize(ref_img, (origin_img.shape[1], origin_img.shape[0])))},
|
||
]
|
||
})
|
||
|
||
# === 步骤2: 粗推理 infer_hairstyle_diy_jy ===
|
||
start = time.time()
|
||
work_dir = os.path.join(userInfo_dir, task_id)
|
||
os.makedirs(work_dir, exist_ok=True)
|
||
import torch
|
||
with torch.no_grad():
|
||
img_res, status, _, landmarks_1k, isEyeOccluded = hairstyle_process.infer_hairstyle_diy_jy(
|
||
origin_img, ref_img, os.path.join(work_dir, task_id), f"{task_id}.png")
|
||
if status != 0:
|
||
raise RuntimeError("发型粗推理失败")
|
||
t_coarse = time.time() - start
|
||
|
||
steps.append({
|
||
"title": "② 粗推理 (infer_hairstyle_diy_jy)",
|
||
"desc": f"用 SPADE 风格迁移模型把目标发型粗略合成到用户脸上。这步只产生粗略效果，细节由后续 SD 推理完善。耗时 {t_coarse:.1f}s",
|
||
"images": [
|
||
{"label": "粗推理结果", "b64": _enc(img_res)},
|
||
]
|
||
})
|
||
|
||
# === 步骤3: 手绘mask作为重绘区（核心区别：完全由用户控制）===
|
||
start = time.time()
|
||
# 手绘mask归一化为 0/255 灰度，保证尺寸与原图一致
|
||
if hand_mask.shape[:2] != origin_img.shape[:2]:
|
||
hand_mask = cv2.resize(hand_mask, (origin_img.shape[1], origin_img.shape[0]),
|
||
interpolation=cv2.INTER_NEAREST)
|
||
if hand_mask.ndim == 3:
|
||
hand_mask = cv2.cvtColor(hand_mask, cv2.COLOR_BGR2GRAY)
|
||
# 二值化（前端传过来已是黑白，这里再保底阈值化）
|
||
_, hand_mask_bin = cv2.threshold(hand_mask, 30, 255, cv2.THRESH_BINARY)
|
||
matting_merge = hand_mask_bin
|
||
|
||
# 统计手绘区域占比，便于调试
|
||
mask_area_ratio = float((hand_mask_bin > 0).sum()) / hand_mask_bin.size * 100
|
||
|
||
# 同时展示自动计算的mask作对比（仅展示，不参与重绘）
|
||
user_material_dir = os.path.join(work_dir, task_id)
|
||
hair_matting_path = os.path.join(user_material_dir, "hair_mask_2.png")
|
||
user_orig_mask_path = os.path.join(user_material_dir, "user_orig_mask.png")
|
||
origin_matting = cv2.imread(user_orig_mask_path, cv2.IMREAD_GRAYSCALE)
|
||
new_matting = cv2.imread(hair_matting_path, cv2.IMREAD_GRAYSCALE)
|
||
auto_merge = None
|
||
if origin_matting is not None and new_matting is not None:
|
||
auto_merge = np.max(np.stack([origin_matting, new_matting], axis=2), axis=2).astype(np.uint8)
|
||
|
||
step3_images = [
|
||
{"label": "用户手绘mask(重绘区)", "b64": _enc_mask(hand_mask_bin)},
|
||
]
|
||
if origin_matting is not None:
|
||
step3_images.append({"label": "自动:原头发mask(仅对比)", "b64": _enc_mask(origin_matting)})
|
||
if new_matting is not None:
|
||
step3_images.append({"label": "自动:新发型mask(仅对比)", "b64": _enc_mask(new_matting)})
|
||
if auto_merge is not None:
|
||
step3_images.append({"label": "自动合并(普通换发型会用)", "b64": _enc_mask(auto_merge)})
|
||
|
||
steps.append({
|
||
"title": "③ 手绘mask（核心：用户控制重绘区）",
|
||
"desc": f"重绘区域完全由用户手绘决定，白色区域={mask_area_ratio:.1f}%。SD 只在这些区域重绘，其余保留原图。下方对比图展示自动计算的mask（仅供参考，不参与本次重绘）。",
|
||
"images": step3_images
|
||
})
|
||
|
||
# === 步骤4: warpAffine 变换 ===
|
||
dst_size = (1152, 1536) if is_hr else (576, 768)
|
||
box_info = hairstyle_process.get_body_info(img_res)
|
||
box_w = box_info[2] - box_info[0]
|
||
box_h = box_info[3] - box_info[1]
|
||
scale = min(dst_size[1] / max(box_h, 1), dst_size[0] / max(box_w, 1))
|
||
rotate_center = [(box_info[2] + box_info[0]) * 0.5, (box_info[3] + box_info[1]) * 0.5]
|
||
M = cv2.getRotationMatrix2D(rotate_center, 0, scale)
|
||
M[:, 2] += np.float32([dst_size[0] * 0.5, dst_size[1] * 0.5]) - np.float32(rotate_center)
|
||
|
||
crop_result = high_quality_warpAffine(img_res, M, dst_size)
|
||
crop_matting = cv2.warpAffine(matting_merge, M, dst_size)
|
||
mask = (crop_matting > 10).astype(np.float32)
|
||
dk = tuple(max(1, int(x)) for x in dilate_kernel)
|
||
mask_dilate = cv2.dilate(mask, np.ones(dk, np.uint8))
|
||
mask_dilate = np.clip(mask_dilate * 255, 0, 255).astype(np.uint8)
|
||
final_img = crop_result
|
||
|
||
steps.append({
|
||
"title": "④ warpAffine 对齐裁剪",
|
||
"desc": f"检测身体框，计算缩放/平移矩阵，把图和mask对齐裁剪到 {dst_size[0]}x{dst_size[1]} 送入 webui。可调：is_hr={is_hr}(决定尺寸), dilate_kernel={dk}",
|
||
"images": [
|
||
{"label": f"裁剪后图({dst_size[0]}x{dst_size[1]})", "b64": _enc(_shrink(crop_result))},
|
||
{"label": f"mask膨胀后(dilate={dk})", "b64": _enc_mask(_shrink(mask_dilate, nearest=True))},
|
||
]
|
||
})
|
||
|
||
# === 步骤5: 读取 config/prompt ===
|
||
config_json_path = os.path.join(material_save_path, "config.json")
|
||
with open(config_json_path, "r") as f:
|
||
in_gender = json.load(f)["gender"]
|
||
images_dir = os.path.join(hair_material_dir, "images")
|
||
txt_dir = os.path.join(images_dir, os.listdir(images_dir)[0])
|
||
txt_path = glob.glob(txt_dir + '/*.txt')[0]
|
||
with open(txt_path, 'r') as f:
|
||
p_tag = f.readline()
|
||
if "titor hairstyle, faceless, no human, gray background, simple background" in p_tag:
|
||
p_tag = p_tag[p_tag.find("simple background, ") + len("simple background, "):]
|
||
else:
|
||
p_tag = ""
|
||
|
||
# === 步骤6: webui 推理（走 photo_service + LoRA）===
|
||
start = time.time()
|
||
sd_result = webui_img2img(
|
||
img=final_img, mask_img=mask_dilate,
|
||
in_gender=in_gender, task_id=task_id,
|
||
hair_id=hair_id, lora_material_path=hair_material_dir,
|
||
tag=p_tag, is_hr=is_hr,
|
||
denoising_strength=denoising_strength, inference_port="57860")
|
||
t_sd = time.time() - start
|
||
|
||
steps.append({
|
||
"title": "⑤ SD 推理 (webui img2img inpainting + LoRA)",
|
||
"desc": f"加载发型LoRA，在mask区域用SD重绘新发型。这是生成发丝细节的关键步骤。耗时 {t_sd:.1f}s。可调：denoising={denoising_strength}（其余 cfg=7/steps=20/sampler=DPM++ 2M Karras/mask_blur=11/seed=123456789 在webui端固定）",
|
||
"images": [
|
||
{"label": "webui输出(SD重绘结果)", "b64": _enc(_shrink(sd_result))},
|
||
]
|
||
})
|
||
|
||
# === 步骤7: warpAffine 贴回原图 ===
|
||
M_inv = cv2.invertAffineTransform(M)
|
||
result_full = origin_img.copy()
|
||
cv2.warpAffine(sd_result, M_inv, (origin_img.shape[1], origin_img.shape[0]),
|
||
dst=result_full, borderMode=cv2.BORDER_TRANSPARENT, flags=cv2.INTER_LANCZOS4)
|
||
|
||
result_strict = origin_img.copy()
|
||
sd_result_back = np.zeros_like(origin_img)
|
||
cv2.warpAffine(sd_result, M_inv, (origin_img.shape[1], origin_img.shape[0]),
|
||
dst=sd_result_back, borderMode=cv2.BORDER_CONSTANT, borderValue=(0, 0, 0), flags=cv2.INTER_LANCZOS4)
|
||
mask_back = np.zeros(origin_img.shape[:2], dtype=np.uint8)
|
||
cv2.warpAffine(mask_dilate, M_inv, (origin_img.shape[1], origin_img.shape[0]),
|
||
dst=mask_back, borderMode=cv2.BORDER_CONSTANT, borderValue=0, flags=cv2.INTER_NEAREST)
|
||
bd = tuple(max(1, int(x)) for x in blend_dilate)
|
||
mask_back = cv2.dilate(mask_back, np.ones(bd, np.uint8))
|
||
# ★ 边缘羽化：对mask_back做高斯模糊，让融合边缘平滑过渡（feather_px=模糊核半径）
|
||
feather_info = ""
|
||
# 先算一份硬边缘版本（feather=0），用于对比展示
|
||
hard_blend = (mask_back.astype(np.float32) / 255)[..., None]
|
||
result_strict_hard = (sd_result_back.astype(np.float32) * hard_blend +
|
||
origin_img.astype(np.float32) * (1 - hard_blend))
|
||
result_strict_hard = np.clip(result_strict_hard, 0, 255).astype(np.uint8)
|
||
result_strict_hard[mask_back == 0] = origin_img[mask_back == 0]
|
||
|
||
if feather_px and feather_px > 0:
|
||
k = max(1, int(feather_px)) * 2 + 1 # 高斯核必须是奇数
|
||
mask_back_blur = cv2.GaussianBlur(mask_back, (k, k), 0)
|
||
mask_blend = (mask_back_blur.astype(np.float32) / 255)[..., None]
|
||
feather_info = f"，边缘羽化{feather_px}px"
|
||
else:
|
||
mask_blend = hard_blend
|
||
result_strict = (sd_result_back.astype(np.float32) * mask_blend +
|
||
origin_img.astype(np.float32) * (1 - mask_blend))
|
||
result_strict = np.clip(result_strict, 0, 255).astype(np.uint8)
|
||
result_strict[mask_back == 0] = origin_img[mask_back == 0]
|
||
|
||
# ★ 羽化对比图：左=硬边缘(feather=0) 右=当前羽化，裁剪mask边界附近放大
|
||
feather_compare = None
|
||
if feather_px and feather_px > 0:
|
||
ys, xs = np.where(mask_back > 10)
|
||
if len(ys) > 0:
|
||
x1 = max(0, xs.min()-20); x2 = min(origin_img.shape[1], xs.max()+20)
|
||
y1 = max(0, ys.min()-20); y2 = min(origin_img.shape[0], ys.max()+20)
|
||
hard_crop = result_strict_hard[y1:y2, x1:x2]
|
||
blur_crop = result_strict[y1:y2, x1:x2]
|
||
sep = np.full((hard_crop.shape[0], 3, 3), 128, dtype=np.uint8)
|
||
feather_compare = np.hstack([hard_crop, sep, blur_crop])
|
||
|
||
result = result_strict if strict_mask else result_full
|
||
|
||
step6_images = [
|
||
{"label": "用户原图", "b64": _enc(origin_img)},
|
||
{"label": "整框覆盖", "b64": _enc(result_full)},
|
||
{"label": "严格mask贴回", "b64": _enc(result_strict)},
|
||
{"label": f"当前选用({'严格mask' if strict_mask else '整框覆盖'})", "b64": _enc(result)},
|
||
]
|
||
if feather_compare is not None:
|
||
step6_images.append({"label": f"★ 羽化对比(左=硬边 右=羽化{feather_px}px)", "b64": _enc(feather_compare)})
|
||
steps.append({
|
||
"title": "⑥ 贴回原图",
|
||
"desc": f"把SD结果逆warpAffine贴回用户原图。可调：strict_mask={strict_mask}, blend_dilate={bd}{feather_info}。整框覆盖=整个裁剪框覆盖原图；严格mask=只在mask区域融合，mask外保留原图",
|
||
"images": step6_images
|
||
})
|
||
|
||
# === 步骤8: 消除接缝（泊松无缝融合）===
|
||
if strict_mask and seamless_blend:
|
||
start_enhance = time.time()
|
||
try:
|
||
sd_back = np.zeros_like(origin_img)
|
||
cv2.warpAffine(sd_result, M_inv, (origin_img.shape[1], origin_img.shape[0]),
|
||
dst=sd_back, borderMode=cv2.BORDER_CONSTANT, borderValue=(0, 0, 0), flags=cv2.INTER_LANCZOS4)
|
||
mask_back2 = np.zeros(origin_img.shape[:2], dtype=np.uint8)
|
||
cv2.warpAffine(mask_dilate, M_inv, (origin_img.shape[1], origin_img.shape[0]),
|
||
dst=mask_back2, borderMode=cv2.BORDER_CONSTANT, borderValue=0, flags=cv2.INTER_NEAREST)
|
||
sd2 = tuple(max(1, int(x)) for x in seamless_dilate)
|
||
mask_back2 = cv2.dilate(mask_back2, np.ones(sd2, np.uint8))
|
||
ys2, xs2 = np.where(mask_back2 > 10)
|
||
if len(ys2) > 10:
|
||
cx2 = int((xs2.min() + xs2.max()) / 2)
|
||
cy2 = int((ys2.min() + ys2.max()) / 2)
|
||
result = cv2.seamlessClone(sd_back, origin_img, mask_back2, (cx2, cy2), cv2.NORMAL_CLONE)
|
||
t_seamless = time.time() - start_enhance
|
||
steps.append({
|
||
"title": "⑦ 泊松融合消除接缝 (seamlessClone)",
|
||
"desc": f"严格mask模式下边缘有接缝/色差。泊松融合保持SD结果内部梯度，把边缘梯度过渡到原图，消除突变。耗时 {t_seamless:.1f}s。可调：seamless_dilate={sd2}",
|
||
"images": [
|
||
{"label": "融合前(有接缝)", "b64": _enc(result_strict)},
|
||
{"label": "融合后(最终)", "b64": _enc(result)},
|
||
]
|
||
})
|
||
except Exception as e:
|
||
steps.append({
|
||
"title": "⑦ 泊松融合（失败）",
|
||
"desc": f"泊松融合失败({e})，回退到严格mask结果",
|
||
"images": [{"label": "最终结果", "b64": _enc(result)}]
|
||
})
|
||
|
||
# === 步骤⑧: enhance 二次增强重绘（可选，让发丝更清晰）===
|
||
# ★ enhance 固定基于「严格mask贴回」的图（result_strict），不受 strict_mask 开关影响
|
||
if enhance:
|
||
start_enh = time.time()
|
||
try:
|
||
from utils import enhance_hair
|
||
# enhance 的输入图固定用严格mask贴回的结果（mask外保留原图）
|
||
enh_input = result_strict
|
||
# ★ enhance 重绘区域 = 原图头发区域 ∪ 手绘mask（并集）
|
||
# origin_matting 是用户原头发mask，hand_mask_bin 是用户手绘mask
|
||
if origin_matting is not None:
|
||
enh_mask = np.max(np.stack([origin_matting, hand_mask_bin], axis=2), axis=2).astype(np.uint8)
|
||
else:
|
||
enh_mask = hand_mask_bin
|
||
# ★ mask 再往外扩大 10%（相对mask外接矩形短边，避免边缘漏掉）
|
||
ys, xs = np.where(enh_mask > 10)
|
||
if len(ys) > 0:
|
||
short_side = min(xs.max() - xs.min(), ys.max() - ys.min())
|
||
dilate_px = max(1, int(short_side * 0.10)) # 短边的10%
|
||
enh_mask = cv2.dilate(enh_mask, np.ones((dilate_px, dilate_px), np.uint8))
|
||
|
||
# ★ 用瞳距换算 3cm = 多少像素（瞳距≈6.3cm）
|
||
# 1k关键点 [691]=左眼中心, [792]=右眼中心
|
||
cm3_px = 0 # 3cm对应的像素数
|
||
try:
|
||
lm = np.asarray(landmarks_1k)
|
||
left_eye = lm[691]; right_eye = lm[792]
|
||
pupil_dist_px = np.linalg.norm(np.array(left_eye) - np.array(right_eye))
|
||
cm3_px = max(1, int(pupil_dist_px / 6.3 * 3)) # 瞳距/6.3cm × 3cm
|
||
except Exception as e:
|
||
print(f"[enhance] 瞳距换算失败({e})，3cm按40px")
|
||
|
||
# ★ 减掉发际线带：从头发下边界向上 3cm 的带状区域
|
||
# 头发下边界 = enh_mask 每列最下面的头发像素；向上3cm内的区域擦除
|
||
enh_mask_before = enh_mask.copy() # 保存减发际线前的mask（可视化用）
|
||
if cm3_px > 0:
|
||
# 找每列头发mask的最下像素行
|
||
cols = np.where(enh_mask.max(axis=0) > 10)[0]
|
||
for c in cols:
|
||
col_ys = np.where(enh_mask[:, c] > 10)[0]
|
||
if len(col_ys) == 0:
|
||
continue
|
||
bottom_y = col_ys.max() # 该列头发最下像素
|
||
# 擦除 [bottom_y - cm3_px, bottom_y] 这一段（发际线带）
|
||
top_erase = max(0, bottom_y - cm3_px)
|
||
enh_mask[top_erase:bottom_y+1, c] = 0
|
||
prompt = "high quality, detailed hair strands, realistic hair texture, sharp focus"
|
||
enhanced = enhance_hair.webui_img2img(enh_input, enh_mask, prompt=prompt,
|
||
denoising_strength=enhance_denoising)
|
||
t_enh = time.time() - start_enh
|
||
# enhance 重绘区域可视化
|
||
try:
|
||
from hairline_mask import make_overlay
|
||
enh_overlay = make_overlay(enh_input, enh_mask, alpha=0.45)
|
||
enh_overlay_before = make_overlay(enh_input, enh_mask_before, alpha=0.45)
|
||
except Exception:
|
||
enh_overlay = enh_input; enh_overlay_before = enh_input
|
||
steps.append({
|
||
"title": "⑧ enhance 二次增强重绘",
|
||
"desc": f"基于「严格mask贴回」图做低强度SD重绘(denoising={enhance_denoising})。重绘区=原图头发∪手绘mask外扩10%({dilate_px}px)，再从发际线向上减掉3cm({cm3_px}px)。耗时 {t_enh:.1f}s",
|
||
"images": [
|
||
{"label": "严格mask贴回(enhance输入)", "b64": _enc(enh_input)},
|
||
{"label": "① 重绘区(外扩后,未减发际线)", "b64": _enc_mask(enh_mask_before)},
|
||
{"label": "② 减发际线带后(最终mask)", "b64": _enc_mask(enh_mask)},
|
||
{"label": "③ 减之前叠加图", "b64": _enc(enh_overlay_before)},
|
||
{"label": "④ 最终mask叠加图", "b64": _enc(enh_overlay)},
|
||
{"label": "⑤ 增强后(最终)", "b64": _enc(enhanced)},
|
||
]
|
||
})
|
||
result = enhanced
|
||
except Exception as e:
|
||
steps.append({
|
||
"title": "⑧ enhance（失败）",
|
||
"desc": f"enhance增强失败({e})，使用未增强结果",
|
||
"images": [{"label": "最终结果", "b64": _enc(result)}]
|
||
})
|
||
|
||
# 清理临时文件
|
||
try:
|
||
shutil.rmtree(user_material_dir)
|
||
os.remove(new_user_img_path)
|
||
except Exception:
|
||
pass
|
||
|
||
params_used = {
|
||
"strict_mask": strict_mask, "seamless_blend": seamless_blend,
|
||
"is_hr": is_hr, "dilate_kernel": list(dilate_kernel),
|
||
"denoising_strength": denoising_strength,
|
||
"blend_dilate": list(blend_dilate), "feather_px": feather_px,
|
||
"seamless_dilate": list(seamless_dilate),
|
||
"enhance": enhance, "enhance_denoising": enhance_denoising,
|
||
"mask_area_ratio_pct": round(mask_area_ratio, 1),
|
||
"gender": in_gender, "tag": p_tag, "dst_size": list(dst_size),
|
||
"total_time": round(time.time() - start_all, 1),
|
||
}
|
||
print(f"[swap_manual] 总耗时: {params_used['total_time']}s")
|
||
return result, steps, params_used
|
||
|
||
|
||
def _shrink(img, max_side=1024, nearest=False):
|
||
"""缩小图片便于前端展示"""
|
||
h, w = img.shape[:2]
|
||
if max(h, w) <= max_side:
|
||
return img
|
||
sc = max_side / max(h, w)
|
||
interp = cv2.INTER_NEAREST if nearest else cv2.INTER_AREA
|
||
return cv2.resize(img, (int(w * sc), int(h * sc)), interpolation=interp)
|
||
|
||
|
||
def _enc(img):
|
||
_, buf = cv2.imencode(".jpg", img, [cv2.IMWRITE_JPEG_QUALITY, 80])
|
||
return base64.b64encode(buf).decode()
|
||
|
||
|
||
def _enc_mask(mask):
|
||
if mask.ndim == 2:
|
||
colored = cv2.applyColorMap(mask, cv2.COLORMAP_JET)
|
||
else:
|
||
colored = mask
|
||
_, buf = cv2.imencode(".jpg", colored, [cv2.IMWRITE_JPEG_QUALITY, 80])
|
||
return base64.b64encode(buf).decode()
|