# SkyworkAI/SkyReels-V2

SkyReels-V2: Infinite-length Film Generative model

Repository: https://github.com/SkyworkAI/SkyReels-V2
Canonical: https://ross.abutalabs.com/products/skyreels-v2
Homepage: https://platform.skyreels.ai
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-01-29T05:21:27+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 64, release rhythm 35, longevity 36
- inputs: {"age_days": 505, "days_push": 216, "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 7462, forks 1627 (observed 2026-08-28T04:09:59.963079+00:00)

## What it is
SkyReels-V2 is an open-source infinite-length film/video generative model using an AutoRegressive Diffusion-Forcing architecture, released with model weights and inference code. It supports text-to-video and image-to-video synthesis, video extension, and start/end frame control.

## Use cases
- generate long videos from text prompts
- image to video synthesis
- extend existing video clips with AI
- generate films of unbounded length
- control start and end frames of generated video
- run state-of-the-art open-source video generation locally

## When to choose
- you need open-source video generation with long or infinite duration
- you want image-to-video or video extension capabilities
- you have GPU resources to run large diffusion models
- you want SOTA autoregressive diffusion video generation

## When to avoid
- you need lightweight or CPU-only video generation
- you want a polished end-user app rather than inference code and weights
- your license requirements demand a standard permissive license

## Facets
- artifact type: library
- maturity: active
- function: video-processing, machine-learning, deep-learning, llm-inference
- domain: artificial-intelligence, deep-learning, media
- platform: python
- tags: video-generation, diffusion-model, autoregressive, text-to-video, image-to-video, diffusion-forcing, film-generation, model-weights, video, gpu, linux

## Member repositories
- SkyworkAI/SkyReels-V2 (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:59.963079+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 2026-08-29T17:37:38.564603+00:00, confidence not recorded.
  - readme: https://github.com/SkyworkAI/SkyReels-V2 (fetched 2026-08-28T04:09:59.963079+00:00, sha eeffd6aa5c17)
- Data as of 2026-08-30T08:39:29.467469+00:00.