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

@ -264,6 +264,7 @@ check_service "GPU Ollama" "http://192.168.178.11:11434/api/version" 3
check_service "GPU STT" "http://192.168.178.11:3020/health" 3
check_service "GPU TTS" "http://192.168.178.11:3022/health" 3
check_service "GPU Image Gen" "http://192.168.178.11:3023/health" 3
check_service "GPU Video Gen" "http://192.168.178.11:3026/health" 3
echo ""
echo "Matrix:"

View file

@ -103,6 +103,7 @@ check_gpu_service "Ollama (LLM)" "http://192.168.178.11:11434/api/version"
check_gpu_service "STT (Whisper)" "http://192.168.178.11:3020/health"
check_gpu_service "TTS" "http://192.168.178.11:3022/health"
check_gpu_service "Image Gen (FLUX)" "http://192.168.178.11:3023/health"
check_gpu_service "Video Gen (LTX)" "http://192.168.178.11:3026/health"
# ============================================
# Network/Tunnel Status