AnimateDiffLoRA

AnimateDiff

This repository is the official implementation of AnimateDiff.

AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

Yuwei Guo, Ceyuan Yang*, Anyi Rao, Yaohui Wang, Yu Qiao, Dahua Lin, Bo Dai

*Corresponding Author

Next

One with better controllability and quality is coming soon. Stay tuned.

Features

• [2023/11/10] Release the Motion Module (beta version) on SDXL, available at Google Drive / HuggingFace / CivitAI. High resolution videos (i.e., 1024x1024x16 frames with various aspect ratios) could be produced with/without personalized models. Inference usually requires ~13GB VRAM and tuned hyperparameters (e.g., #sampling steps), depending on the chosen personalized models. Checkout to the branch sdxl for more details of the inference. More checkpoints with better-quality would be available soon. Stay tuned. Examples below are manually downsampled for fast loading.

 <tr style="line-height: 0">
  <td width=50% style="border: none; text-align: center">Original SDXL</td>
  <td width=30% style="border: none; text-align: center">Personalized SDXL</td>
  <td width=20% style="border: none; text-align: center">Personalized SDXL</td>
  </tr>
  <tr>
  <td width=50% style="border: none"><img src="__assets__/animations/motion_xl/01.gif"></td>
  <td width=30% style="border: none"><img src="__assets__/animations/motion_xl/02.gif"></td>
  <td width=20% style="border: none"><img src="__assets__/animations/motion_xl/03.gif"></td>
  </tr>

• [2023/09/25] Release MotionLoRA and its model zoo, enabling camera movement controls! Please download the MotionLoRA models (74 MB per model, available at Google Drive / HuggingFace / CivitAI ) and save them to the models/MotionLoRA folder. Example:

  python -m scripts.animate --config configs/prompts/v2/5-RealisticVision-MotionLoRA.yaml
  

  Zoom In		Zoom Out		Zoom Pan Left		Zoom Pan Right
  Tilt Up		Tilt Down		Rolling Anti-Clockwise		Rolling Clockwise

• [2023/09/10] New Motion Module release! mm_sd_v15_v2.ckpt was trained on larger resolution & batch size, and gains noticeable quality improvements. Check it out at Google Drive / HuggingFace / CivitAI and use it with configs/inference/inference-v2.yaml. Example:

  python -m scripts.animate --config configs/prompts/v2/5-RealisticVision.yaml
  

  Here is a qualitative comparison between mm_sd_v15.ckpt (left) and mm_sd_v15_v2.ckpt (right):

• GPU Memory Optimization, ~12GB VRAM to inference

Quick Demo

User Interface developed by community:

• A1111 Extension sd-webui-animatediff (by @continue-revolution)
• ComfyUI Extension ComfyUI-AnimateDiff-Evolved (by @Kosinkadink)
• Google Colab: Colab (by @camenduru)

We also create a Gradio demo to make AnimateDiff easier to use. To launch the demo, please run the following commands:

conda activate animatediff
python app.py

By default, the demo will run at localhost:7860.

Model Zoo

Motion Modules

| Name | Parameter | Storage Space | |----------------------|-----------|---------------| | mm_sd_v14.ckpt | 417 M | 1.6 GB | | mm_sd_v15.ckpt | 417 M | 1.6 GB | | mm_sd_v15_v2.ckpt | 453 M | 1.7 GB |

MotionLoRAs

| Name | Parameter | Storage Space | |--------------------------------------|-----------|---------------| | v2_lora_ZoomIn.ckpt | 19 M | 74 MB | | v2_lora_ZoomOut.ckpt | 19 M | 74 MB | | v2_lora_PanLeft.ckpt | 19 M | 74 MB | | v2_lora_PanRight.ckpt | 19 M | 74 MB | | v2_lora_TiltUp.ckpt | 19 M | 74 MB | | v2_lora_TiltDown.ckpt | 19 M | 74 MB | | v2_lora_RollingClockwise.ckpt | 19 M | 74 MB | | v2_lora_RollingAnticlockwise.ckpt | 19 M | 74 MB |

Common Issues

Installation

Please ensure the installation of xformer that is applied to reduce the inference memory.

Various resolution or number of frames

Currently, we recommend users to generate animation with 16 frames and 512 resolution that are aligned with our training settings. Notably, various resolution/frames may affect the quality more or less.

How to use it without any coding

1) Get lora models: train lora model with A1111 based on a collection of your own favorite images (e.g., tutorials English, Japanese, Chinese) or download Lora models from Civitai.

2) Animate lora models: using gradio interface or A1111 (e.g., tutorials English, Japanese, Chinese)

3) Be creative togther with other techniques, such as, super resolution, frame interpolation, music generation, etc.

Animating a given image

We totally agree that animating a given image is an appealing feature, which we would try to support officially in future. For now, you may enjoy other efforts from the talesofai.

Contributions from community

Contributions are always welcome!! The dev branch is for community contributions. As for the main branch, we would like to align it with the original technical report :)

Training and inference

Please refer to ANIMATEDIFF for the detailed setup.

Gallery

We collect several generated results in GALLERY.

BibTeX

@article{guo2023animatediff,
  title={AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning},
  author={Guo, Yuwei and Yang, Ceyuan and Rao, Anyi and Wang, Yaohui and Qiao, Yu and Lin, Dahua and Dai, Bo},
  journal={arXiv preprint arXiv:2307.04725},
  year={2023}
}

Disclaimer

This project is released for academic use. We disclaim responsibility for user-generated content. Users are solely liable for their actions. The project contributors are not legally affiliated with, nor accountable for, users' behaviors. Use the generative model responsibly, adhering to ethical and legal standards.

Contact Us

Yuwei Guo: guoyuwei@pjlab.org.cn
Ceyuan Yang: yangceyuan@pjlab.org.cn
Bo Dai: daibo@pjlab.org.cn

Acknowledgements

Codebase built upon Tune-a-Video.