feat(调试): 接口2女性生发分步耗时分析页面

新增 /api/v1/debug/grow-timing 调试接口 + debug_grow_timing.html 测试页:
- 拆分接口2女性生发的每一步并独立计时(extract_context/mask/swap/blend/comfyui)
- 测试页用条形图展示各步耗时占比,附步骤说明
- 用于定位性能瓶颈,优化方向判断

实测花瓣发型: 总11.9s = 预处理0.44s + 换发型4.4s + ComfyUI重绘6.8s

app.py

@@ -813,6 +813,143 @@ async def hair_grow(
         return err(1007, f"处理失败：{ex}")
 
 
+# ---------------------------------------------------------------------------
+# 调试接口：接口2 女性生发 分步计时
+# ---------------------------------------------------------------------------
+@app.post(
+    "/api/v1/debug/grow-timing",
+    summary="调试-接口2女性生发分步计时",
+    tags=["调试"],
+    include_in_schema=False,
+)
+async def debug_grow_timing(
+    image_file: Optional[UploadFile] = File(default=None),
+    image_url: Optional[str] = Form(default=None),
+    image_base64: Optional[str] = Form(default=None),
+    hair_style: str = Form(default="2", description="发型序号(花瓣=2)，逗号分隔多选"),
+):
+    """单图跑接口2女性生发，返回每个步骤的耗时 + 结果图，用于定位性能瓶颈。
+
+    步骤拆分：
+      1. extract_context：人脸关键点检测 + 头发分割 + 发际线几何
+      2. [每个发型] generate_hairline_redraw：
+         2a. compute_mask：发际线遮罩计算
+         2b. _call_swap：调 change_hair 换发型（内含 webui SD1.5 推理，远程或本机）
+         2c. _composite：接缝融合（多频段/羽化）
+      3. [每个发型] _call_local_redraw：调本机 ComfyUI 用 Flux.2 重绘
+    """
+    import time as _time
+    from fastapi.concurrency import run_in_threadpool
+
+    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:
+        max_styles = 5
+        hair_styles = _parse_hair_styles(hair_style, max_styles)
+        if hair_styles is None:
+            return err(1007, f"hair_style 必须为 1..{max_styles}")
+
+        t_total0 = _time.perf_counter()
+        timings = {"total_ms": 0, "extract_context_ms": 0, "per_hairstyle": []}
+
+        # 步骤1: extract_context
+        t0 = _time.perf_counter()
+        from hairline.service import extract_context as _ec, _call_local_redraw, _REDRAW_MAX_SIDE  # noqa
+        from face_analysis.hairline_grow import generate_hairline_redraw, NoFaceError  # noqa
+        from face_analysis.head_mask import SEGFORMER_HAIR  # noqa
+        ctx = await run_in_threadpool(_ec, image)
+        timings["extract_context_ms"] = int((_time.perf_counter() - t0) * 1000)
+        if ctx is None:
+            return err(1001, "无法识别人像")
+
+        hair_mask_reuse = (ctx["parse_map"] == SEGFORMER_HAIR)
+        h, w = image.shape[:2]
+        eff_side = _REDRAW_MAX_SIDE
+        redraw_img, hair_mask_redraw = image, hair_mask_reuse
+        downscale_info = None
+        if eff_side > 0 and max(h, w) > eff_side:
+            from hairline.service import _downscale_max_side
+            redraw_img, _rs = _downscale_max_side(image, eff_side)
+            _nh, _nw = redraw_img.shape[:2]
+            if hair_mask_redraw is not None:
+                hair_mask_redraw = cv2.resize(hair_mask_reuse.astype(np.uint8), (_nw, _nh),
+                                              interpolation=cv2.INTER_NEAREST).astype(bool)
+            downscale_info = {"from": f"{w}x{h}", "to": f"{_nw}x{_nh}", "max_side": eff_side}
+
+        textures_map = None
+        from hairline.service import get_texture_map, _FEMALE_KEY_TO_CHANG, load_texture_rgba, build_overlay_layer, load_ext_mesh
+        textures = get_texture_map()["female"]
+        items = [(s, textures[s - 1]) for s in hair_styles]
+
+        for order, (key, white_path) in items:
+            hs_t0 = _time.perf_counter()
+            entry = {"hairline_type": key, "order": order}
+            chang_id = _FEMALE_KEY_TO_CHANG.get(key)
+            entry["chang_id"] = chang_id
+            entry["ok"] = False
+            entry["error"] = None
+            entry["grown_b64"] = None
+            if chang_id is None:
+                entry["error"] = f"无对应 chang_id"
+                timings["per_hairstyle"].append(entry)
+                continue
+            try:
+                # 2a/2b/2c: generate_hairline_redraw (内部含 mask+swap+blend)
+                t0 = _time.perf_counter()
+                data = await run_in_threadpool(
+                    generate_hairline_redraw, redraw_img, chang_id,
+                    hair_mask=hair_mask_redraw, **_V2_FINAL_DEFAULTS)
+                t_redraw_pipeline = _time.perf_counter() - t0
+                _tm = data.get("timings_ms") or {}
+                entry["mask_ms"] = _tm.get("mask", 0)
+                entry["swap_ms"] = _tm.get("swap", 0)
+                entry["blend_ms"] = _tm.get("blend", 0)
+                entry["redraw_pipeline_ms"] = int(t_redraw_pipeline * 1000)
+
+                steps = data.get("steps") or {}
+                final_b64 = steps.get("final_base64") or ""
+                mask_b64 = steps.get("redraw_band_mask_base64") or ""
+                if not final_b64 or not mask_b64:
+                    entry["error"] = f"final/遮罩缺失(final={len(final_b64)} mask={len(mask_b64)})"
+                    timings["per_hairstyle"].append(entry)
+                    continue
+                if final_b64.startswith("data:"):
+                    final_b64 = final_b64.split(",", 1)[1]
+                if mask_b64.startswith("data:"):
+                    mask_b64 = mask_b64.split(",", 1)[1]
+
+                # 3: ComfyUI 重绘
+                t0 = _time.perf_counter()
+                grown_png = await run_in_threadpool(
+                    _call_local_redraw,
+                    base64.b64decode(final_b64), base64.b64decode(mask_b64))
+                entry["comfyui_redraw_ms"] = int((_time.perf_counter() - t0) * 1000)
+                if grown_png:
+                    entry["grown_b64"] = "data:image/jpeg;base64," + _png_to_jpg_b64(grown_png)
+                    entry["ok"] = True
+                else:
+                    entry["error"] = "ComfyUI 重绘返回空"
+            except NoFaceError:
+                entry["error"] = "未检出人脸"
+            except Exception as ex:  # noqa: BLE001
+                entry["error"] = str(ex)[:150]
+            entry["hairstyle_total_ms"] = int((_time.perf_counter() - hs_t0) * 1000)
+            timings["per_hairstyle"].append(entry)
+
+        timings["total_ms"] = int((_time.perf_counter() - t_total0) * 1000)
+        timings["downscale"] = downscale_info
+        timings["image_size"] = f"{w}x{h}"
+        return ok(timings)
+    except Exception as ex:  # noqa: BLE001
+        logger.exception("debug/grow-timing 异常")
+        return err(1007, f"处理失败：{ex}")
+
+
 # ---------------------------------------------------------------------------
 # 接口 7：C 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）。