Features
End-to-end short-video generation from text prompt
Multi-model AI orchestration (DeepSeek, Qwen, GLM, Kling v2.5, faster-whisper, multiple TTS)
Circuit breaker pattern for resilient API calls
Usage metering and quota tracking per tenant
Full-stack observability (Langfuse, cross-language trace_id propagation)
Prompt anchoring for consistent visual identity
CLIP-based text-image consistency scoring and gating
Automatic audio-video synchronization rescue (4-tier strategy)
SSE progress streaming for real-time job status
Single-segment regeneration without full rebuild
Spring Boot API gateway with JWT auth and routing
FastAPI orchestration with async workers (ARQ)
Vue.js frontend (Vue Flow, Pinia, Tailwind)
Docker Compose one-click deployment
Database persistence via SQLAlchemy + Alembic migrations (PostgreSQL/Redis/MinIO)
Text-to-video generation up to 60 seconds
Animate static images into video
Extend and fill existing video footage
Temporal consistency across frames
Complex scene composition with multiple characters
Realistic physics and lighting simulation
Dynamic camera movements (pan, zoom, track)
High-resolution output up to 1080p
Object permanence for long sequences
Support for detailed text prompts and styles
