#177 · Primary category: Video & Animation

ai-shortVideo-pipeline

ai ai-pipeline circuit-breaker clip-model deepseek docker-compose failover fastapi ffmpeg java kling langfuse llm multi-model prompt-engineering python resilience4j short-video spring-boot video-generation

End-to-end AI short-video production pipeline. FastAPI orchestration + Spring Boot gateway with multi-model failover, circuit breaker, metering, and full-stack observability. AI quality gating: prompt anchoring, CLIP consistency, AV sync auto-rescue.

Project last updated:08/06/26

GitHub Stars

576

Forks

95

Contributors

2

License

MIT

Why we included this project

This project is a full production line for short videos, not just a generator. It runs the whole chain, from topic discovery and script writing through image and video generation, TTS narration, and post-production, as a seven-layer pipeline, with a FastAPI core doing the orchestration and a Spring Boot gateway handling routing, auth, rate limits, and failover. The quality-control layer is where it gets interesting: prompt anchoring keeps a subject's visual identity consistent across segments, CLIP checks reject keyframes that drift off-prompt early, and an audio-video sync rescue can adjust tempo, pad video, or rewrite narration to fix mismatches. It is built for Chinese-language content and runs via Docker Compose, with cross-language tracing through Langfuse and per-tenant metering included.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category