# AILab-CVC/VideoCrafter

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

Repository: https://github.com/AILab-CVC/VideoCrafter
Canonical: https://ross.abutalabs.com/products/videocrafter
Homepage: https://ailab-cvc.github.io/videocrafter2/
Language: Python
License: NOASSERTION
License Family: other
Topics: image-to-video, text-to-video, video-generation
Last push: 2026-01-09T15:01:22+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 61, release rhythm 8, longevity 89
- inputs: {"age_days": 1248, "days_push": 236, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5073, forks 413 (observed 2026-08-28T04:09:09.392860+00:00)

## What it is
VideoCrafter is an open-source video generation and editing toolbox built on video diffusion models, offering Text-to-Video and Image-to-Video generation. VideoCrafter2 improves visual quality, motion, and concept composition over the original model despite limited training data.

## Use cases
- generate videos from text prompts
- create video from a single image
- produce short AI-generated film clips
- run text-to-video diffusion models locally
- research video diffusion model training

## When to choose
- you need open-source text-to-video or image-to-video generation with local model weights
- you want a research-grade video diffusion codebase to build on
- you need better motion quality and concept composition than VideoCrafter1

## When to avoid
- you need long-form or high-resolution video generation rather than short clips
- you lack a GPU or want a fully managed hosted video generation API
- you need a no-code commercial video editing tool

## Facets
- artifact type: library
- maturity: active
- function: video-processing, machine-learning, deep-learning, image-processing
- domain: artificial-intelligence, deep-learning, media
- platform: python
- tags: text-to-video, image-to-video, video-diffusion, generative-ai, video-generation, diffusion-models, video, gpu, linux

## Member repositories
- AILab-CVC/VideoCrafter (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:09.392860+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 2026-08-29T18:02:47.175770+00:00, confidence not recorded.
  - readme: https://github.com/AILab-CVC/VideoCrafter (fetched 2026-08-28T04:09:09.392860+00:00, sha e3bf54763930)
  - homepage: https://ailab-cvc.github.io/videocrafter2/ (fetched 2026-08-29T08:57:33.543089+00:00, sha 5514bf28b3a8)
- Data as of 2026-08-30T08:39:29.467469+00:00.