kabachuha/sd-webui-text2video

Auto1111 extension implementing text2video diffusion models (like ModelScope or VideoCrafter) using only Auto1111 webui dependencies

44
/ 100
Emerging

Supports multiple text2video architectures (ModelScope, VideoCrafter, ZeroScope, Potat1) with LoRA fine-tuning, inpainting, and seamless video looping capabilities. Leverages Torch2/xformers attention optimizations to achieve extended frame generation (125+ frames) within modest VRAM constraints (6-12GB). Integrates directly into Auto1111's UI via WebAPI, with automatic model hotswapping and configurable VAE/sampling strategies.

1,326 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

1,326

Forks

115

Language

Python

License

Last pushed

Jul 14, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/kabachuha/sd-webui-text2video"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.