chiyiandDevin
e7a4613bac
vivid 的 quality 就是模型自己的档位字符串——图像 1K/2K/4K、视频 720p/1080p。之前映射成 OpenAI 的 low/medium/high 导致视频上游收到 "1K" 报 4001 "该模型支持 720p"。现在原样透传,空值才默认 1K。 Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Vivid AI Backend
Go backend for vivid-ai, using:
- Gin
- GORM
- PostgreSQL
- Redis
Current scope
This is an in-progress rewrite. The current skeleton already includes:
- app bootstrap
- PostgreSQL and Redis initialization
- GORM auto-migrations
- session storage in Redis
- image access control for
/images/:user/:name - public site endpoint:
/admin/api/site - public showcase endpoint:
/admin/api/showcase - session-based auth endpoint:
/admin/api/auth/me
Environment
Set these before running:
$env:POSTGRES_DSN="host=127.0.0.1 user=postgres password=postgres dbname=vivid_ai port=5432 sslmode=disable TimeZone=Asia/Shanghai"
$env:REDIS_ADDR="127.0.0.1:6379"
$env:HTTP_ADDR=":6061"
Optional:
$env:APP_ENV="development"
$env:APP_TITLE="Vivid AI"
$env:SESSION_COOKIE_NAME="vivid_session"
$env:CORS_ORIGINS="http://localhost:5173,http://127.0.0.1:5173"
Run
go run ./cmd/api
Notes
- Generated media defaults to
../../ai-gateway/data/generatedrelative to the backend working directory. - Private images require either:
- session cookie
- bearer session token
- bearer API key
- Showcase images are public.