本轮(生图模型选择 + 火山接入): - 工作室新增「生图模型」选择器(模特上身图/平台套图头部 chip + 图片创作底部 Pill), 默认火山 Seedream,可切 gpt-image-2;选择写入 localStorage,下次进页面读回 - 后端 resolve_image_model 解析所选模型;enqueue_standalone_images 接 image_model - worker 按模型能力分流:有 image_edit(gpt-image)走多图编辑;无(火山)走 image_generation(image=参考图);新增 _ratio_to_volcano_size 让火山按比例出图 → 内衣等敏感品类用火山可绕开 gpt-image 的 sexual 内容审核 模特上身图提示词: - 穿戴/非穿戴分流、按 index 变化动作场景镜头、负面词尾接、多图参考序号自适应 - _product_reference_urls:商品参考真实上传图优先、排除 AI 生成图、可多张 其他(并入此前各会话未提交改动): - 图片创作多会话(ImageConversation + migration 0019)、任务中心按类型过滤 - accounts/projects/assets/team/auth 等零散调整、相关测试 - 测试脚本(tryon_*.py)、测试清单(core/bug/*.xlsx)
AirShelf Backend
All backend code lives under AirShelf/core/backend by project decision.
Local bootstrap
cd /Users/maidong/Desktop/zyc/qiyuan_gitea/AirShelf/core/backend
python3.12 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env
python manage.py migrate
python manage.py runserver 0.0.0.0:8000
Start workers in separate terminals:
cd /Users/maidong/Desktop/zyc/qiyuan_gitea/AirShelf/core/backend
source .venv/bin/activate
celery -A airshelf worker -l info -P threads -c 4 # 线程池 4 并发(出图/视频可并行;勿用 -P solo 串行)
ffmpeg must be available on PATH for Stage5 export jobs.
Runtime layout
- Django project:
airshelf - Domain apps:
apps/* - Settings module:
airshelf.settings.development - Celery app:
airshelf.celery
Secrets must be supplied by environment variables or .env; never commit values from account.md.
Useful commands
python manage.py check
python manage.py makemigrations --check --dry-run
python manage.py migrate
python manage.py bootstrap_volcano_models
python manage.py test apps.accounts apps.projects apps.billing