ai-shortVideo-pipeline
End-to-end AI short-video production pipeline. FastAPI orchestration + Spring Boot gateway with multi-model failover, circuit breaker, metering, and full-stack
What is ai-shortVideo-pipeline?
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.
Overview of ai-shortVideo-pipeline
What it is
An end-to-end automated short-video production pipeline. One command in, a publish-ready video out. It uses FastAPI as the orchestration core and a Java gateway as the platform governance layer (auth / routing / circuit breaker / metering / observability), coordinating multiple AI models for generation and quality gating.
Key features
- Seven-layer pipeline architecture: Topic (L1) → Creative (L2) → Visual (L3) → Audio (L4) → Post-production (L5) → Distribution (L6) → Optimization (L7). Layers are decoupled and independently replaceable.
- Multi-model failover + circuit breaker: Java gateway aggregates DeepSeek / Qwen / GLM with Resilience4j protection; failed providers are automatically rotated.
- AI consistency governance: prompt anchoring (maintain visual identity of subjects across video segments), CLIP text-image consistency gating (reject off-prompt keyframes early), audio-video sync auto-rescue (4-tier strategy: audio tempo / video pad / narration rewrite).
- Full-stack observability: trace_id propagated across Java/Python; Langfuse call-tree visibility.
- Metering & rate limiting: AOP aspect captures token / cost without code changes, aggregated by tenant.
- Production-ready: SSE progress streaming, single-segment regeneration, rolling log archives.
Use cases
- Hot-news commentary
- Knowledge explainers
- Emotional storytelling
- Curiosity / strange facts
- Social insight clips
Getting started
### 1. Clone and prepare env
git clone .git
cd myAiVideos
cp .env.example .env
### Edit .env to fill in at least the required AI provider API keys.
### 2. Start backend (postgres + redis + orchestrator + worker)
docker compose up -d postgres redis orchestrator worker
### 3. Run database migrations
docker compose exec -T orchestrator alembic upgrade head
### 4. (Optional) Start Java gateway
docker compose up -d gateway
### 5. Start frontend
cd sl-vue && npm install && npm run dev
License and pricing
MIT — open source.
Based on the project's public README and repository metadata.