# zai-org/SCAIL-2

Official Implementation of SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning

Repository: https://github.com/zai-org/SCAIL-2
Canonical: https://ross.abutalabs.com/products/scail-2
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-24T13:30:59+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 6
- inputs: {"age_days": 97, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1132, forks 87 (observed 2026-08-28T04:03:42.717836+00:00)

## What it is
Official implementation of SCAIL-2, an open-source model for end-to-end controlled character animation that drives character videos from reference images and motion sources without intermediate pose representations. It provides inference and training code, a relighting LoRA, multi-reference support, and ComfyUI integration.

## Use cases
- animate a character image from a driving video
- generate character animation videos without skeleton pose maps
- replace a character in a video with a reference identity
- animate multiple characters from a single driving source
- train a custom character animation model
- use character animation nodes in ComfyUI workflows

## When to choose
- you need production-quality pose-driven character video generation
- your driving source is complex motion or non-human (animals) where skeleton-based methods fail
- you want an open-source alternative with training code and ComfyUI support

## When to avoid
- you only need lightweight real-time animation on CPU
- you need simple image editing rather than video generation
- you lack a GPU with sufficient VRAM for large video diffusion models

## Facets
- artifact type: library
- maturity: active
- function: video-processing, machine-learning, deep-learning, image-processing
- domain: computer-vision, artificial-intelligence, deep-learning
- platform: python
- tags: character-animation, pose-driven-video-generation, diffusion-model, inference, comfyui-integration, lora, motion-transfer, video, gpu, linux

## Member repositories
- zai-org/SCAIL-2 (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:42.717836+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 2026-08-30T06:38:00.061804+00:00, confidence not recorded.
  - readme: https://github.com/zai-org/SCAIL-2 (fetched 2026-08-28T04:03:42.717836+00:00, sha 90af2dad8bbc)
- Data as of 2026-08-30T08:39:29.467469+00:00.