v110-v112 自定义模式完善 + 模板导出增强 + 多模态兼容优化

- 自定义模式:分析模型输出 delta 唯一改动指令,生图模板 custom_image_prompt.md({delta} 占位符),不再使用负向提示词;generate_design 按 custom_mode 分支,Pinterest 模式保留原创化指令,两模式互不影响
- 多模态分析 response_format 三级回退(json_schema → json_object → none),兼容 DeepSeek
- 模板导出:details 扩展列(细节1/2/3)、target_audience 扩展列(适用人群1)、固定值风格1=休闲/风格2=运动
- 童装特征库更新 + 标题模板外部化 + 图源映射增强
This commit is contained in:
2026-09-03 18:28:39 +08:00
parent d68cc3b9e3
commit 5ab5cf6586
40 changed files with 1967 additions and 149 deletions
+1
View File
@@ -75,6 +75,7 @@ def _enrich_briefs(raw_briefs: List[Dict[str, Any]], country: str,
"design_category": classify(term),
"concept": f"围绕「{term}」的原创印花设计",
"image_prompt": str(b.get("image_prompt") or "").strip(),
"delta": str(b.get("delta") or "").strip(),
"ref_images": [str(p) for p in (b.get("ref_images") or []) if str(p)],
"source_md5": str(b.get("source_md5") or "").strip().lower(),
"brief_id": str(b.get("brief_id") or "").strip(),