feat(接口2): 支持动态切换Flux模型+分辨率 + 模型对比测试脚本

代码改动:
- comfyui.py: run() 新增 unet_name 参数，提交前自动改写模型节点
  (.gguf→UnetLoaderGGUF, .safetensors→UNETLoader)，并按模型自动同步
  文本编码器(4b→qwen_3_4b, 9b→qwen_3_8b)，避免切换时维度不匹配
- redraw.py: run_redraw() 透传 unet_name
- service.py: generate_grow_results_swap/generate_grow_results 支持
  redraw_max_side(分辨率参数化) 和 unet_name 透传
- app.py: 接口2 新增 flux_model/redraw_max_side 两个 Form 参数(男女路径都加)
- test_interface2.html: 新增 Flux模型/压图长边 下拉选择器
- add_hair.json/0716add-hair-api.json: 工作流默认模型改为 9b

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

清理:
- .gitignore: 排除 benchmark_out/、报告HTML、gateway.log、*.bak.*
- 移除 gateway.log 的 git 跟踪

benchmark_matrix.py

@@ -0,0 +1,129 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""接口2女性 花瓣形 单发型 4模型×3分辨率×3图×3次 矩阵测试。
+
+调用本机 hair-worker (:8187) 的 /api/v1/hair/grow，gender=female, hair_style=2(花瓣形)。
+每次记录：生发图、耗时、显存峰值。结果图存到 benchmark_out/matrix/，最后生成 HTML 报告。
+"""
+import base64
+import json
+import os
+import subprocess
+import sys
+import time
+from pathlib import Path
+
+import requests
+
+API = "http://127.0.0.1:8187/api/v1/hair/grow"
+TOKEN = "dev-shared-secret-2026"
+OUT = Path("/home/ubuntu/hair/benchmark_out/matrix")
+OUT.mkdir(parents=True, exist_ok=True)
+
+# 4 模型 × 3 分辨率 × 3 图 × 3 次
+MODELS = [
+    ("4b-fp8", "flux-2-klein-4b-fp8.safetensors"),
+    ("9b-fp8", "flux2.0/flux-2-klein-9b-fp8.safetensors"),
+    ("9b-Q5", "flux-2-klein-9b-Q5_K_M.gguf"),
+    ("9b-Q4", "flux-2-klein-9b-Q4_K_M.gguf"),
+]
+RES = [("orig", "0"), ("640", "640"), ("896", "896")]
+IMGS = [
+    ("asdf", "/home/ubuntu/hair/image/asdf.jpg"),
+    ("qwer", "/home/ubuntu/hair/image/qwer.jpg"),
+    ("girl5", "/home/ubuntu/hair/image/girl_img/girl5.jpg"),
+]
+REPEAT = 3
+
+
+def gpu_used():
+    """返回当前显存已用 MiB。"""
+    try:
+        out = subprocess.check_output(
+            ["nvidia-smi", "--query-gpu=memory.used", "--format=csv,noheader,nounits"],
+            timeout=10,
+        )
+        return int(out.decode().strip())
+    except Exception:
+        return 0
+
+
+def call(img_path, model_file, res_val):
+    """调一次接口2。返回 dict: ok/elapsed/grown_path/gpu_peak/error。"""
+    fd = {
+        "gender": "female",
+        "hair_style": "2",  # 花瓣形
+        "use_mask": "true",
+        "prompt": "填充遮罩区域的头发，皮肤加一点磨皮，再加一点美颜",
+    }
+    if model_file:
+        fd["flux_model"] = model_file
+    if res_val != "":
+        fd["redraw_max_side"] = res_val
+    t0 = time.perf_counter()
+    peak = gpu_used()
+    err = None
+    grown_path = None
+    try:
+        with open(img_path, "rb") as f:
+            r = requests.post(
+                API, headers={"X-Internal-Token": TOKEN},
+                files={"image_file": (os.path.basename(img_path), f, "image/jpeg")},
+                data=fd, timeout=300,
+            )
+        elapsed = time.perf_counter() - t0
+        # 采样峰值（推理刚结束）
+        peak = max(peak, gpu_used())
+        j = r.json()
+        if j.get("code") != 0:
+            err = f"code={j.get('code')} {j.get('message','')}"
+        else:
+            res = j.get("data", {}).get("results", [])
+            if res and res[0].get("grown_image_base64"):
+                grown_path = OUT / f"tmp_grown.jpg"
+                with open(grown_path, "wb") as gf:
+                    gf.write(base64.b64decode(res[0]["grown_image_base64"]))
+            elif res:
+                err = "grown_image_base64 为空"
+            else:
+                err = "无 results"
+    except Exception as e:
+        elapsed = time.perf_counter() - t0
+        err = str(e)[:200]
+    return {"elapsed": elapsed, "gpu_peak": peak, "grown_path": str(grown_path) if grown_path else None, "error": err}
+
+
+def main():
+    results = []  # 每元素一个组合
+    total = len(MODELS) * len(RES) * len(IMGS) * REPEAT
+    idx = 0
+    for mlabel, mfile in MODELS:
+        for rlabel, rval in RES:
+            for ilabel, ipath in IMGS:
+                # 一个组合：3 次
+                runs = []
+                for rep in range(REPEAT):
+                    idx += 1
+                    print(f"[{idx}/{total}] {mlabel} | res={rlabel} | {ilabel} | rep{rep+1}", flush=True)
+                    r = call(ipath, mfile, rval)
+                    print(f"    -> {r['elapsed']:.1f}s  peak={r['gpu_peak']}MiB  err={r['error']}", flush=True)
+                    # 存每次的生发图
+                    if r["grown_path"]:
+                        save_to = OUT / f"{mlabel}_{rlabel}_{ilabel}_r{rep+1}.jpg"
+                        os.replace(r["grown_path"], save_to)
+                        r["grown_path"] = str(save_to)
+                    runs.append(r)
+                results.append({
+                    "model": mlabel, "model_file": mfile,
+                    "res": rlabel, "res_val": rval,
+                    "img": ilabel, "img_path": ipath,
+                    "runs": runs,
+                })
+    # 存原始数据
+    with open(OUT / "results.json", "w", encoding="utf-8") as f:
+        json.dump(results, f, ensure_ascii=False, indent=2)
+    print(f"\n✓ 全部完成，原始数据 -> {OUT/'results.json'}", flush=True)
+
+
+if __name__ == "__main__":
+    main()