Quantized GGUF version of SCAIL-2 for ComfyUI.
Original model link: https://huggingface.co/zai-org/SCAIL-Preview
Watch us on Youtube: @VantageWithAI
SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning
SCAIL-2 is an open-source model for end-to-end controlled character animation. It animates a reference character with a driving video, and also supports character replacement and multi-character scenarios without relying on intermediate pose representations.
🔎 Overview
Prior approaches to character animation depend heavily on intermediate representations such as skeleton maps or inpainting masks. These intermediates are ambiguous under complex motion, restrict driving sources to human movements, and limit the reach of replacement and multi-character animation.
SCAIL-2 removes this dependence and achieve End-to-end Driving. Using several off-the-shelf models (SCAIL-Preview, Wan-Animate, MoCha), 60K motion pairs were synthesized and trained through a Unified Motion Transfer Interface with dedicated masking channels and RoPE design. The reverse driving training recipe with the unification lets the model learn capabilities beyond its teacher models, yielding emergent abilities such as:
- Cross-identity character replacement
- Animal-driving scenarios
- Zero-shot support for advanced control intermediates like SAM3D-Body mesh rendering
📦 Model
| Item | Detail |
|---|---|
| Resolutions | End-to-end driving supports both 512p and 704p; pose-driven and replacement performs better at 704p |
| Constraints | H and W must both be divisible by 32 (e.g. 704×1280) |
| Training | Mixed resolutions and fps |
📄 Citation
@article{yan2025scail,
title={SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations},
author={Yan, Wenhao and Ye, Sheng and Yang, Zhuoyi and Teng, Jiayan and Dong, ZhenHui and Wen, Kairui and Gu, Xiaotao and Liu, Yong-Jin and Tang, Jie},
journal={arXiv preprint arXiv:2512.05905},
year={2025}
}