git clone https://github.com/guoyww/AnimateDiff.git cd AnimateDiff pip install -r requirements.txt

Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.
AnimateDiff adds motion to existing Stable Diffusion checkpoints without retraining them, turning any image model into an animation model.
| Category | AI video generation |
| Type | Animation module |
| License | Apache-2.0 |
| Runs locally | Yes |
| Built with | Python |
| Skill level | Intermediate |
| Best for | animating your existing SD models |
Other open-source ai video generation tools worth comparing:
Open-SoraOpen video generation you can run
Wan2.1State-of-the-art open video model
HunyuanVideoTencent's large open video model
LTX-VideoReal-time-class video generation
FramePackLong video on modest VRAM
Mochi 1High-fidelity open video generation
CogVideoText and image to videoAnimateDiff is free and open-source (Apache-2.0 license), so you can use, self-host and modify it at no cost.
Yes. AnimateDiff is designed to run on your own machine or server, keeping your data private.
Popular open-source alternatives include Open-Sora, Wan2.1, HunyuanVideo. See the comparisons above to choose.
Browse the full directory of open-source AI tools, models and projects — updated daily.
Browse all tools →