# ali-vilab/VGen

Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models

Repository: https://github.com/ali-vilab/VGen
Canonical: https://ross.abutalabs.com/products/vgen
Homepage: https://i2vgen-xl.github.io
Language: Python
License Family: other
Topics: diffusion-models, video-synthesis
Last push: 2025-01-10T09:09:13+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 73
- inputs: {"age_days": 1031, "days_push": 600, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license, no_readme
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3155, forks 274 (observed 2026-08-28T04:07:46.296604+00:00)

## What it is
VGen is the official repository for a holistic video generation ecosystem built on diffusion models, including the I2VGen-XL cascaded image-to-video synthesis approach. It provides code and models for high-quality text-to-video and image-to-video generation up to 1280x720 resolution.

## Use cases
- generate videos from a static image
- text-to-video synthesis with diffusion models
- train or fine-tune video generation models
- research cascaded diffusion models for video
- produce high-resolution 720p AI-generated video clips

## When to choose
- you need state-of-the-art image-to-video generation with pretrained models
- you are researching or extending diffusion-based video synthesis
- you want an open ecosystem covering training and inference for video generation

## When to avoid
- you need a production-ready API or hosted service rather than research code
- you lack a GPU or cannot handle large model requirements
- you need a permissively licensed dependency and the missing license is a blocker

## Facets
- artifact type: library
- maturity: active
- function: video-processing, machine-learning, deep-learning
- domain: artificial-intelligence, deep-learning, image-processing
- platform: python
- tags: diffusion-models, video-generation, text-to-video, image-to-video, i2vgen-xl, research-code, video, linux, gpu

## Member repositories
- ali-vilab/VGen (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:46.296604+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 2026-08-30T07:25:39.099540+00:00, confidence not recorded.
  - homepage: https://i2vgen-xl.github.io (fetched 2026-08-29T09:40:10.666597+00:00, sha fd6b5f89f968)
- Data as of 2026-08-30T08:39:29.467469+00:00.