AnimateDiff
Animate your Stable Diffusion checkpoints with plug-in motion modules.
- Stars
- 12.3K
- Forks
- 1.1K
- Open issues
- 320
- Last commit
- 2024-07-31
Live from the GitHub API · updated 2026-10-15
What is AnimateDiff?
AnimateDiff adds a motion module to existing Stable Diffusion models, so any community checkpoint or LoRA can produce short animations. Most people use it via ComfyUI or A1111 extensions.
Key features
- Works with existing SD1.5 checkpoints and LoRAs
- Motion LoRAs for camera moves
- SparseCtrl for keyframe/sketch control
System requirements
- Platforms
- Linux · Windows
- GPU
- NVIDIA
- VRAM
- 8–12 GB
How to install AnimateDiff
Summarized from the project’s README. Projects change quickly — check the GitHub page for the latest instructions.
Reference code
- 1Clone and install.
git clone https://github.com/guoyww/AnimateDiff.git cd AnimateDiff pip install -r requirements.txt - 2Download motion modules as described in the README and run a config.
python -m scripts.animate --config configs/prompts/1_animate/1_1_animate_RealisticVision.yaml
Strengths
- Reuses your favorite SD styles
- Huge community of workflows
Limitations
- Short, low-resolution clips
- Older SD1.5-era quality
AnimateDiff alternatives compared
| Software | Stars | License | Platforms | VRAM |
|---|---|---|---|---|
| AnimateDiff Animate your Stable Diffusion checkpoints with plug-in motion modules. | 12.3K | Apache-2.0 | 8–12 GB | |
| FramePack Long image-to-video generation on laptop GPUs with as little as 6 GB VRAM. | 17.3K | Apache-2.0 | 6 GB minimum | |
| Wan 2.2 Alibaba’s open-weight video generation models (text, image and speech to video). | 17.9K | Apache-2.0 | 24 GB for TI2V-5B at 720p; 80 GB-class GPUs (or offloading) for A14B models | |
| LTX-Video Fast, real-time-capable open video generation from Lightricks. | 11.1K | Apache-2.0 | 12 GB+ for smaller variants; more for 13B models | |
| HunyuanVideo Tencent’s 13B-parameter open video foundation model. | 12.6K | Tencent Hunyuan Community License | 45 GB minimum, 60–80 GB recommended for 720p (per README); less with community quantizations | |
| CogVideoX Open text-to-video and image-to-video models from Zhipu AI / Tsinghua. | 13.1K | Apache-2.0 | ~12–24 GB depending on model and optimizations (see the README table) |
Related models
FAQ
Is AnimateDiff free?
Yes — AnimateDiff is open-source software released under the Apache-2.0 license. Check the license (and any model weight licenses) before commercial use.
Does AnimateDiff run on Windows, Mac and Linux?
AnimateDiff supports: Linux, Windows.
What hardware do I need for AnimateDiff?
NVIDIA. VRAM: 8–12 GB
How do I install AnimateDiff?
1. Clone and install. 2. Download motion modules as described in the README and run a config.
What are the best AnimateDiff alternatives?
Popular alternatives include FramePack, Wan 2.2, LTX-Video, HunyuanVideo. See the comparison table on this page.
Can I use AnimateDiff online without installing it?
If you don’t have a large GPU, AiLoft runs Veo 3.1 and Kling 2.5 in the cloud — generate and compare clips in the browser.
No 24 GB GPU? Generate AI video online
Run Veo 3.1 and Kling 2.5 in the cloud and compare clips side by side — pay per clip.