Mirrors/AnimateDiff
1
0
Fork 0
mirror of https://github.com/guoyww/AnimateDiff.git synced 2026-04-03 09:46:36 +02:00
Code Issues Packages Projects Releases Wiki Activity
Files
3e555502043d3c76a50170b589d4d64a582393fe
AnimateDiff/README.md

209 lines
11 KiB
Markdown
Raw Normal View History

update readme
2023-07-03 00:32:41 +08:00
# AnimateDiff
update readme
2023-07-11 10:54:17 +08:00
This repository is the official implementation of [AnimateDiff](https://arxiv.org/abs/2307.04725).
update readme
2023-07-03 00:32:41 +08:00
update readme
2023-07-11 10:54:17 +08:00
**[AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://arxiv.org/abs/2307.04725)**
update readme
2023-07-03 00:32:41 +08:00
</br>
Yuwei Guo,
update readme
2023-07-03 01:13:53 +08:00
Ceyuan Yang*,
update readme
2023-07-03 00:32:41 +08:00
Anyi Rao,
Yaohui Wang,
Yu Qiao,
Dahua Lin,
update readme
2023-07-03 01:13:53 +08:00
Bo Dai
update
2023-07-09 23:37:00 +08:00
<p style="font-size: 0.8em; margin-top: -1em">*Corresponding Author</p>
update readme
2023-07-03 00:32:41 +08:00
update
2023-07-21 10:36:35 +08:00
<!-- [Arxiv Report](https://arxiv.org/abs/2307.04725) | [Project Page](https://animatediff.github.io/) -->
[![arXiv](https://img.shields.io/badge/arXiv-2307.04725-b31b1b.svg)](https://arxiv.org/abs/2307.04725)
[![Project Page](https://img.shields.io/badge/Project-Website-green)](https://animatediff.github.io/)
[![Open in OpenXLab](https://cdn-static.openxlab.org.cn/app-center/openxlab_app.svg)](https://openxlab.org.cn/apps/detail/Masbfca/AnimateDiff)
[![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-yellow)](https://huggingface.co/spaces/guoyww/AnimateDiff)
update readme
2023-07-03 00:32:41 +08:00
update readme
2023-11-03 09:49:15 +08:00
## Next
One with better controllability and quality is coming soon. Stay tuned.
update readme
2023-09-25 11:39:05 +08:00
update "usage without coding", fix hyperlink
2023-07-20 12:58:29 -07:00
## Features
update readme regarding sdxl
2023-11-10 11:55:23 +08:00
- **[2023/11/10]** Release the Motion Module (beta version) on SDXL, available at [Google Drive](https://drive.google.com/file/d/1EK_D9hDOPfJdK4z8YDB8JYvPracNx2SX/view?usp=share_link
) / [HuggingFace](https://huggingface.co/guoyww/animatediff/blob/main/mm_sdxl_v10_beta.ckpt
update readme
2023-11-10 11:59:27 +08:00
) / [CivitAI](https://civitai.com/models/108836/animatediff-motion-modules). 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](https://github.com/guoyww/AnimateDiff/tree/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.
update readme regarding sdxl
2023-11-10 11:55:23 +08:00
<table class="center">
<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>
</table>
update readme
2023-09-25 11:39:05 +08:00
- **[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](https://drive.google.com/drive/folders/1EqLC65eR1-W-sGD0Im7fkED6c8GkiNFI?usp=sharing) / [HuggingFace](https://huggingface.co/guoyww/animatediff) / [CivitAI](https://civitai.com/models/108836/animatediff-motion-modules) ) and save them to the `models/MotionLoRA` folder. Example:
```
python -m scripts.animate --config configs/prompts/v2/5-RealisticVision-MotionLoRA.yaml
```
<table class="center">
<tr style="line-height: 0">
<td colspan="2" style="border: none; text-align: center">Zoom In</td>
<td colspan="2" style="border: none; text-align: center">Zoom Out</td>
<td colspan="2" style="border: none; text-align: center">Zoom Pan Left</td>
<td colspan="2" style="border: none; text-align: center">Zoom Pan Right</td>
</tr>
<tr>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_01/01.gif"></td>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_02/02.gif"></td>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_01/02.gif"></td>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_02/01.gif"></td>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_01/03.gif"></td>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_02/04.gif"></td>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_01/04.gif"></td>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_02/03.gif"></td>
</tr>
<tr style="line-height: 0">
Update shot camera movement term
2023-09-25 19:51:52 -07:00
<td colspan="2" style="border: none; text-align: center">Tilt Up</td>
<td colspan="2" style="border: none; text-align: center">Tilt Down</td>
update readme
2023-09-25 11:39:05 +08:00
<td colspan="2" style="border: none; text-align: center">Rolling Anti-Clockwise</td>
<td colspan="2" style="border: none; text-align: center">Rolling Clockwise</td>
</tr>
<tr>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_01/05.gif"></td>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_02/05.gif"></td>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_01/06.gif"></td>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_02/06.gif"></td>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_01/07.gif"></td>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_02/07.gif"></td>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_01/08.gif"></td>
<td style="border: none"><img src="__assets__/animations/motion_lora/model_02/08.gif"></td>
</tr>
</table>
- **[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](https://drive.google.com/drive/folders/1EqLC65eR1-W-sGD0Im7fkED6c8GkiNFI?usp=sharing) / [HuggingFace](https://huggingface.co/guoyww/animatediff) / [CivitAI](https://civitai.com/models/108836/animatediff-motion-modules) and use it with `configs/inference/inference-v2.yaml`. Example:
update readme
2023-09-10 21:25:55 +08:00
```
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):
<table class="center">
<tr>
<td><img src="__assets__/animations/compare/old_0.gif"></td>
<td><img src="__assets__/animations/compare/new_0.gif"></td>
<td><img src="__assets__/animations/compare/old_1.gif"></td>
<td><img src="__assets__/animations/compare/new_1.gif"></td>
<td><img src="__assets__/animations/compare/old_2.gif"></td>
<td><img src="__assets__/animations/compare/new_2.gif"></td>
<td><img src="__assets__/animations/compare/old_3.gif"></td>
<td><img src="__assets__/animations/compare/new_3.gif"></td>
</tr>
</table>
update "usage without coding", fix hyperlink
2023-07-20 12:58:29 -07:00
- GPU Memory Optimization, ~12GB VRAM to inference
update readme
2023-11-03 09:49:15 +08:00
## Quick Demo
User Interface developed by community:
add comfyui
2023-10-15 13:35:49 -07:00
- A1111 Extension [sd-webui-animatediff](https://github.com/continue-revolution/sd-webui-animatediff) (by [@continue-revolution](https://github.com/continue-revolution))
- ComfyUI Extension [ComfyUI-AnimateDiff-Evolved](https://github.com/Kosinkadink/ComfyUI-AnimateDiff-Evolved) (by [@Kosinkadink](https://github.com/Kosinkadink))
- Google Colab: [Colab](https://colab.research.google.com/github/camenduru/AnimateDiff-colab/blob/main/AnimateDiff_colab.ipynb) (by [@camenduru](https://github.com/camenduru))
update README
2023-07-16 10:40:59 +08:00
update readme
2023-11-03 09:49:15 +08:00
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`.
<br><img src="__assets__/figs/gradio.jpg" style="width: 50em; margin-top: 1em">
update readme
2023-09-25 11:39:05 +08:00
## Model Zoo
<details open>
<summary>Motion Modules</summary>
| 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 |
</details>
<details open>
<summary>MotionLoRAs</summary>
| 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 |
correct shot name
2023-09-30 00:23:01 +08:00
| v2_lora_TiltUp.ckpt | 19 M | 74 MB |
| v2_lora_TiltDown.ckpt | 19 M | 74 MB |
update readme
2023-09-25 11:39:05 +08:00
| v2_lora_RollingClockwise.ckpt | 19 M | 74 MB |
| v2_lora_RollingAnticlockwise.ckpt | 19 M | 74 MB |
</details>
update README
2023-07-16 10:40:59 +08:00
## Common Issues
<details>
<summary>Installation</summary>
update "usage without coding", fix hyperlink
2023-07-20 12:58:29 -07:00
update README
2023-07-16 10:40:59 +08:00
Please ensure the installation of [xformer](https://github.com/facebookresearch/xformers) that is applied to reduce the inference memory.
</details>
update "usage without coding", fix hyperlink
2023-07-20 12:58:29 -07:00
update README
2023-07-16 10:40:59 +08:00
<details>
<summary>Various resolution or number of frames</summary>
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.
</details>
update "usage without coding", fix hyperlink
2023-07-20 12:58:29 -07:00
<details>
<summary>How to use it without any coding</summary>
1) Get lora models: train lora model with [A1111](https://github.com/continue-revolution/sd-webui-animatediff) based on a collection of your own favorite images (e.g., tutorials [English](https://www.youtube.com/watch?v=mfaqqL5yOO4), [Japanese](https://www.youtube.com/watch?v=N1tXVR9lplM), [Chinese](https://www.bilibili.com/video/BV1fs4y1x7p2/))
or download Lora models from [Civitai](https://civitai.com/).
2) Animate lora models: using gradio interface or A1111
(e.g., tutorials [English](https://github.com/continue-revolution/sd-webui-animatediff), [Japanese](https://www.youtube.com/watch?v=zss3xbtvOWw), [Chinese](https://941ai.com/sd-animatediff-webui-1203.html))
3) Be creative togther with other techniques, such as, super resolution, frame interpolation, music generation, etc.
</details>
update README
2023-07-16 10:40:59 +08:00
<details>
<summary>Animating a given image</summary>
update "usage without coding", fix hyperlink
2023-07-20 12:58:29 -07:00
update README
2023-07-16 10:40:59 +08:00
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](https://github.com/talesofai/AnimateDiff).
</details>
<details>
<summary>Contributions from community</summary>
update
2023-07-19 23:32:30 +08:00
Contributions are always welcome!! The <code>dev</code> branch is for community contributions. As for the main branch, we would like to align it with the original technical report :)
update README
2023-07-16 10:40:59 +08:00
</details>
update readme
2023-11-03 09:49:15 +08:00
## Training and inference
Please refer to [ANIMATEDIFF](./__assets__/docs/animatediff.md) for the detailed setup.
gradio
2023-07-18 16:41:22 +08:00
add bashscripts
2023-07-09 22:40:48 +08:00
## Gallery
update readme
2023-11-03 09:49:15 +08:00
We collect several generated results in [GALLERY](./__assets__/docs/gallery.md).
update readme: community cases
2023-07-13 17:40:54 +08:00
update
2023-07-10 13:46:01 +08:00
## BibTeX
update readme
2023-07-11 10:54:17 +08:00
```
update README
2023-07-16 10:40:59 +08:00
@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}
update readme
2023-07-11 10:54:17 +08:00
}
```
add bashscripts
2023-07-09 22:40:48 +08:00
update
2023-07-10 13:52:01 +08:00
## Contact Us
**Yuwei Guo**: [guoyuwei@pjlab.org.cn](mailto:guoyuwei@pjlab.org.cn)
**Ceyuan Yang**: [yangceyuan@pjlab.org.cn](mailto:yangceyuan@pjlab.org.cn)
**Bo Dai**: [daibo@pjlab.org.cn](mailto:daibo@pjlab.org.cn)
add bashscripts
2023-07-09 22:40:48 +08:00
## Acknowledgements
Update shot camera movement term
2023-09-25 19:51:52 -07:00
Codebase built upon [Tune-a-Video](https://github.com/showlab/Tune-A-Video).
Reference in New Issue Copy Permalink