# kabachuha/sd-webui-text2video

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

Repository: https://github.com/kabachuha/sd-webui-text2video
Canonical: https://ross.abutalabs.com/products/sd-webui-text2video
Language: Python
License: NOASSERTION
License Family: other
Topics: automatic1111, extension, gradio, modelscope, stable-diffusion, text2video, webui, videocrafter
Last push: 2024-07-14T07:14:03+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 90
- inputs: {"age_days": 1263, "days_push": 780, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1322, forks 114 (observed 2026-08-28T04:04:22.095090+00:00)

## What it is
An Automatic1111 WebUI extension that adds text-to-video generation using diffusion models like ModelScope and VideoCrafter, relying only on the webui's existing dependencies. It supports prompt weights, LoRAs, frame interpolation/inpainting, and a WebAPI.

## Use cases
- generate short videos from text prompts inside stable diffusion webui
- run modelscope text2video locally without extra logins
- animate an existing image into a video
- create seamless looping videos with diffusion models
- use trained text-to-video LoRAs in the webui
- generate anime-style video clips from prompts

## When to choose
- you already use the Automatic1111 Stable Diffusion WebUI and want text-to-video without a separate install
- you have limited VRAM and need low-VRAM video generation options
- you want ModelScope or VideoCrafter models with LoRA and prompt-weight support

## When to avoid
- you need a production-grade or actively developed text-to-video pipeline
- you want state-of-the-art video generation beyond ModelScope/VideoCrafter
- you don't use the Automatic1111 WebUI
- you need long high-resolution videos on modest hardware

## Facets
- artifact type: plugin
- maturity: maintenance
- function: video-processing, stable-diffusion, machine-learning, llm-inference
- domain: artificial-intelligence, image-processing, media
- platform: python, cross-platform
- tags: automatic1111-extension, text2video, modelscope, videocrafter, gradio, stable-diffusion, video-generation, video, gpu, web-server

## Member repositories
- kabachuha/sd-webui-text2video (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:22.095090+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:47:14.301845+00:00, confidence not recorded.
  - readme: https://github.com/kabachuha/sd-webui-text2video (fetched 2026-08-28T04:04:22.095090+00:00, sha c8b3ba04cd09)
- Data as of 2026-08-30T08:39:29.467469+00:00.