feat(mana-video-gen): add AI video generation service with LTX-Video

New GPU service for fast text-to-video generation using LTX-Video (~2B params)
on the RTX 3090. Generates 480p clips in 10-30 seconds, uses ~10GB VRAM.
Includes Cloudflare Tunnel route, Prometheus monitoring, and health checks.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Till JS 2026-04-02 01:17:47 +02:00
parent 28b953255b
commit 06107f6a52
13 changed files with 1017 additions and 0 deletions

View file

@ -183,6 +183,7 @@ manacore-monorepo/
│ ├── mana-media/ # Media platform: CAS, thumbnails (Hono + Bun)
│ ├── mana-llm/ # LLM abstraction (Python/FastAPI)
│ ├── mana-image-gen/ # AI image generation with FLUX (Python/FastAPI)
│ ├── mana-video-gen/ # AI video generation with LTX-Video (Python/FastAPI)
│ ├── mana-stt/ # Speech-to-text (Python/FastAPI)
│ ├── mana-tts/ # Text-to-speech (Python/FastAPI)
│ ├── mana-voice-bot/ # Voice assistant (Python/FastAPI)
@ -920,6 +921,7 @@ Host mana-gpu
- Mana STT (Speech-to-Text, Port 3020)
- Mana TTS (Text-to-Speech, Port 3022)
- Mana Image Gen (FLUX image generation, Port 3023)
- Mana Video Gen (LTX-Video generation, Port 3026)
For setup documentation, see **[docs/WINDOWS_GPU_SERVER_SETUP.md](docs/WINDOWS_GPU_SERVER_SETUP.md)**.