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
+2
View File
@@ -188,6 +188,8 @@ class MockBackend:
"image_prompt": (f"{motif}, {art_style}, {palette}, {composition}, "
f"original {art_style} t-shirt print design, "
f"no brand logo, no trademark, no character, no watermark"),
# 自定义模式 mock 兜底:给一个具体改动指令(模板 {delta} 占位符替换用)
"delta": "change the main subject to face the opposite direction",
# 生图参考:每条简报对应其来源爬取图(mock 按图逐张产出简报,顺序一一对应)
"ref_images": [str(paths[i])] if i < len(paths) else [],
"source": "pinterest",