diff --git a/apps/worker/worker_app/tasks/viral_video.py b/apps/worker/worker_app/tasks/viral_video.py
index 678c3b8d0..58272d7eb 100644
--- a/apps/worker/worker_app/tasks/viral_video.py
+++ b/apps/worker/worker_app/tasks/viral_video.py
@@ -444,6 +444,121 @@ def _analyze_single_image(
                     _parts.append(f"{_skin}肤色")
                     _parts.append(f"{_face}脸型")
                     _parts.append(f"身着{_outfit}")
+                    if _pose != "无法判断":
+                        _parts.append(f"姿态{_pose}")
+                    if _expr != "无法判断":
+                        _parts.append(f"表情{_expr}")
+                    else:
+                        _parts.append("表情自然")
+                    # #2186: 智能回填——VLM有时省略hair/outfit等外貌属性，但product.name/features/colors里已有相关信息
+                    # 从product名字和features中提取服装关键词回填outfit
+                    if _outfit in ("日常服装", "无法判断"):
+                        for _ppn in product_nodes:
+                            _pn = (_ppn.get("attrs") or {}).get("name", "") or ""
+                            _pf = (_ppn.get("attrs") or {}).get("features", "") or ""
+                            _ptxt = _pn + " " + _pf
+                            # 服装关键词识别（常见上装/下装/裙装/套装）
+                            _cloth_kws = [
+                                "衬衫",
+                                "T恤",
+                                "毛衣",
+                                "针织衫",
+                                "卫衣",
+                                "外套",
+                                "西装",
+                                "夹克",
+                                "风衣",
+                                "大衣",
+                                "羽绒服",
+                                "马甲",
+                                "背心",
+                                "连衣裙",
+                                "半身裙",
+                                "短裙",
+                                "长裙",
+                                "牛仔裤",
+                                "休闲裤",
+                                "西裤",
+                                "运动裤",
+                                "短裤",
+                                "旗袍",
+                                "汉服",
+                                "制服",
+                                "polo衫",
+                                "POLO衫",
+                                "针织",
+                                "毛衫",
+                                "开衫",
+                                "帽衫",
+                                "皮夹克",
+                                "皮衣",
+                            ]
+                            for _ckw in _cloth_kws:
+                                if _ckw in _ptxt:
+                                    # 提取含关键词的短语（关键词前后4字）
+                                    _ci = _ptxt.find(_ckw)
+                                    _start = max(0, _ci - 6)
+                                    _end = min(len(_ptxt), _ci + len(_ckw) + 2)
+                                    _outfit_extract = _ptxt[_start:_end].strip(" ,，。.、")
+                                    # 清理掉品牌名/产品名词的干扰（只取服装描述部分）
+                                    _outfit_extract = re.sub(
+                                        r"^[\w一-龥]{0,2}(牌|品牌|的|款|女|男|新|装|大|小|长|短|厚|薄)",
+                                        "",
+                                        _outfit_extract,
+                                    )
+                                    if len(_outfit_extract) >= 2:
+                                        _outfit = _outfit_extract
+                                        break
+                            if _outfit not in ("日常服装", "无法判断"):
+                                break
+                    # 从color标签中提取头发颜色回填hair
+                    if _hair in ("自然发型", "无法判断"):
+                        _hair_color = ""
+                        _color_nodes = [n for n in nodes if n["tag"] == "color"]
+                        _hair_kws_map = {
+                            "黑": "黑色",
+                            "棕": "棕色",
+                            "金": "金色",
+                            "栗": "栗色",
+                            "红": "红色",
+                            "白": "白色",
+                            "灰": "灰色",
+                            "蓝": "蓝色",
+                            "黄": "黄色",
+                            "紫": "紫色",
+                        }
+                        for _cn in _color_nodes:
+                            _cname = (_cn.get("attrs") or {}).get("name", "") or ""
+                            # 小占比颜色更可能是发色（非主色的小面积色），且名称含头发/黑/棕/金等
+                            _ccov = 0.0
+                            try:
+                                _ccov = float((_cn.get("attrs") or {}).get("coverage", "0") or 0)
+                            except Exception:
+                                pass
+                            for _hk, _hv in _hair_kws_map.items():
+                                if _hk in _cname and _ccov < 0.3:
+                                    _hair_color = _hv
+                                    break
+                            if _hair_color:
+                                break
+                        if _hair_color:
+                            _hair = f"{_hair_color}头发"
+                        else:
+                            _hair = "自然发型"
+                    # 重新拼装_parts（回填后）
+                    _parts = []
+                    if _gender != "无法判断":
+                        _g = _gender + ("性" if not _gender.endswith("性") else "")
+                        _parts.append(_g)
+                    else:
+                        _parts.append("成年人")
+                    if _age != "无法判断":
+                        _parts.append(_age)
+                    _parts.append("人物")
+                    _parts.append(_hair)
+                    _parts.append(f"{_skin}肤色")
+                    _parts.append(f"{_face}脸型")
+                    _parts.append(f"身着{_outfit}")
                     if _pose != "无法判断":
                         _parts.append(f"姿态{_pose}")
                     if _expr != "无法判断":
@@ -452,7 +567,7 @@ def _analyze_single_image(
                         _parts.append("表情自然")
                     portrait_prompt = "，".join(_parts)
                     logger.info(
-                        "[爆款视频] 图片 #%d 解析<people>: count=%d gender=%s age=%s hair=%s skin=%s face=%s outfit=%s pose=%s expr=%s → %s",
+                        "[爆款视频] 图片 #%d 解析<people>(回填后): count=%d gender=%s age=%s hair=%s skin=%s face=%s outfit=%s pose=%s expr=%s → %s",
                         idx,
                         _count,
                         _gender,
diff --git a/packages/application/viral_video/prompts.py b/packages/application/viral_video/prompts.py
index 4e41733a9..bf131b1e1 100644
--- a/packages/application/viral_video/prompts.py
+++ b/packages/application/viral_video/prompts.py
@@ -65,7 +65,10 @@ hair/skin_tone/face_shape/outfit四项绝对禁止填“无法判断”，必须
 - outfit：必须描述可见穿着，如“米色翻领衬衫”“白色T恤”“黑色连衣裙”
 即使局部被遮挡也要根据可见部分合理推断；确实看不清时按最接近的直观印象描述。
 
-其他非人物属性看不到或无法判断时填“无法判断”，布尔值填false，不要留空标签。"""
+其他非人物属性看不到或无法判断时填“无法判断”，布尔值填false，不要留空标签。
+
+【有人物场景输出参考（女性手持商品示例，必须写全10个属性，禁止省略）】
+<people has_person="true" count="1" gender="女" age_range="青年" hair="黑色齐肩直发" skin_tone="暖调自然肤色" face_shape="鹅蛋脸" outfit="米色翻领衬衫" pose="正面半身，手持商品" expression="面带微笑"/>"""
 
 _IMAGE_ANALYSIS_USER = """请分析以下商品图片，共 {image_count} 张。
 所属行业：{industry}