SCAIL
Animates a character from an image using motion from another video, including complex turns and multiple characters. SCAIL-2 works without an intermediate skeleton and can replace a character in a clip.
- Developer
- Zhipu AI (Z.ai) and Tsinghua University, China
- First release
- Dec 2025
- Latest release
- Jun 2026
- Sizes
- 14B
- License
- Commercial use allowedMIT (weights on HF), code — Apache 2.0
- Ready-made builds
- GGUF
- Running
- On your own serverNeeds a GPU
- Industries
- Media and production, Marketing and content
What it does
- Transferring an actor's motion to a character
- Replacing a character in a finished video
- Animating mascots and illustrations
Where it is used
Hardware requirements
Versions
- SCAIL-2
- SCAIL-Preview (14B)
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.
Frequently asked questions
Can SCAIL be used in a commercial project?
Yes. License: MIT (weights on HF), code — Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.
What hardware does SCAIL need?
At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does SCAIL support Russian?
Language does not matter for this model: it does not work with text.
Where can I download SCAIL and what does it cost?
The SCAIL weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.
How I deploy it for clients
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
Text-to-video and image-to-video; the small version runs on a gaming GPU. After 2.2 only applied models are open: editing (VACE), audio-driven talking characters (S2V), dancing to music (Dancer).
DetailsAvatarsLivePortraitKuaishou (Kling) · ChinaCommercial use allowedAnimates a portrait from a reference video: an actor's facial expressions and head turns are transferred to the photo. Runs fast even on a weak GPU.
DetailsVideoAnimateDiffShanghai AI Lab and CUHK · ChinaCommercial use allowedA module that brings Stable Diffusion image models to life, turning them into short animations. One of the first open video technologies.
DetailsSource: huggingface.co/zai-org/SCAIL-2. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


