🎬 AI-powered manga & animation video generation pipeline. Write a story → auto-split into scenes → AI-generate frames → dub → publish. Runs entirely on open-source models via ComfyUI.
Write any story or prompt. The system automatically splits it into scenes, generates manga-style frames, and assembles them into a video.
Zero-cost text-to-speech via Piper TTS. Each character gets distinct voice lines synced to the animation timeline.
Docker Compose brings up the entire pipeline — ComfyUI sidecar, web interface, and job runner — with a single command.
Designed for content factories. Queue multiple stories, process them in parallel, and publish results automatically.
Swap models, change art styles, add new workflows — everything is driven by ComfyUI workflows and config files.
Built for solo creators. No subscriptions, no API fees, no hidden costs. Your hardware, your content.
# Clone
git clone https://github.com/chfr19820610-cell/AIComics.git
cd AIComics
# Launch
docker compose up -d
# Open http://localhost:8080 and start creating! Story Input (text or prompt)
│
▼
Scene Splitter ──► Frame Generator (ComfyUI)
│ │
▼ ▼
Script Writer Image Assembler
│ │
▼ ▼
TTS (Piper) ──► Audio Sync ──► Video Export
│
▼
Publish / Share