Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Fine-Grained Open Domain Image Animation with Motion Guidance
| Date | Stars |
|---|---|
| 2026-07-24 | 967 |
| 2026-07-25 | 967 |
| 2026-07-28 | 967 |
| 2026-07-30 | 967 |
| 2026-08-06 | 967 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<h2><center>👉 AnimateAnything: Fine Grained Open Domain Image Animation with Motion Guidance</h2>
[Zuozhuo Dai](), [Zhenghao Zhang](), [Menghao Li](), [Junchao Liao](), [Siyu Zhu](), [Long Qin](), [Weizhi Wang]()
<a href='https://arxiv.org/abs/2311.12886'><img src='https://img.shields.io/badge/ArXiv-2311.12886-red'></a>
<a href='https://animationai.github.io/AnimateAnything/'><img src='https://img.shields.io/badge/Project-Page-Blue'></a> 
<!-- views since 24.04 -->
</div>
## Friendship Link 🔥
- We are excited to announce the open-source release of our latest work: [Tora: Trajectory-oriented Diffusion Transformer for Video Generation](https://github.com/alibaba/Tora). It is the first trajectory-oriented DiT framework that concurrently integrates textual, visual, and trajectory conditions for video generation.
## Showcases
https://github.com/alibaba/animate-anything/assets/1107525/e2659674-c813-402a-8a85-e620f0a6a454
<table>
<tr>
<th>Input Image with Mask</th>
<th>Prompt</th>
<th>Result</th>
</tr>
<tr>
<td><img src="docs/sample_1.png" alt="Input image" width="180" height="170" /></td>
<td align="center">
Barbie watching the camera with a smiling face.</td>
<td><img src="docs/sample_1.gif" alt="Result" width="180" height="170" /></td>
</tr>
<tr>
<td><img src="docs/sample_2.png" alt="Input image" width="180" height="180" /></td>
<td align="center">
The cloak swaying in the wind.</td>
<td><img src="docs/sample_2.gif" alt="Result" width="180" height="180" /></td>
</tr>
<tr>
<td><img src="docs/sample_3.png" alt="Input image" width="180" height="180" /></td>
<td align="center">
A red fish is swimming.</td>
<td><img src="docs/sample_3.gif" alt="Result" width="180" height="180" /></td>
</tr>
</table>
<!-- | Reference Image | Motion Mask | GIF |
| ------------- | ------------- | -------- |
|  |  |  The fish and tadpoles are playing.| -->
## Framework
## News 🔥
**2024.2.5**: Support multiple GPUs training with Accelerator DeepSpeed. Config DeepSpeed zero_stage 2 and offload_optimizer_device cpu, you can do full finetuning animate-anything with 4x16G V100 GPUs and SVD with 4x24G A10 GPUs now.
**2023.12.27**: Support finetuning based on SVD (stable video diffusion) model. Update SVD based animate_anything_svd_v1.0
**2023.12.18**: Update model to animate_anything_512_v1.02
## Features Planned
- 💥 Transparent video generatinon. (Take a RGBA image as input and output animated RGBA videos)
- ✅ reproduce Transparent VAE encoder and decoder according to [LayerDiffuse](https://github.com/layerdiffusion/sd-forge-layerdiffuse).
- ✅ finetune 3D-Unet to support the basic RGBA-image-to-RGBA-video capability.
- 💥 Enhanced prompt-following: generating long-detailed captions using LLaVA.
- 💥 Replace the U-Net with DiffusionTransformer (DiT) as the base model.
- 💥 Variable resolutions and aspect ratios.
- 💥 Support Huggingface Demo / Google Colab.
- ✅ support svd video2video Google Colab demo. See colab.ipynb.
- ✅ Support LoRA finetuning.
- etc.
## Getting Started
This repository is based on [Text-To-Video-Finetuning](https://github.com/ExponentialML/Text-To-Video-Finetuning.git).
### Create Conda Environment (Optional)
It is recommended to install Anaconda.
**Windows Installation:** https://docs.anaconda.com/anaconda/install/windows/
**Linux Installation:** https://docs.anaconda.com/anaconda/install/linux/
```bash
conda create -n animation python=3.10
conda activate animation
```
### Python Requirements
```bash
pip install -r requirements.txt
```
## Running inference
Please download the [pretrained model](https://cloudbook-public-production.oss-cn-shanghai.aliyuncs.com/animation/animate_anything_512_v1.02.tar) to outputExcerpt of 10,411 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8a64ef0442158966, topic:video-generation, topic:animation, readme:video generation
