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.
Code for SCIS-2025 Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".
| Date | Stars |
|---|---|
| 2026-07-24 | 1190 |
| 2026-07-25 | 1188 |
| 2026-07-28 | 1188 |
| 2026-07-30 | 1188 |
| 2026-08-06 | 1188 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<!-- main documents --> <div align="center"> # UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation [Xiang Wang](https://scholar.google.com.hk/citations?user=cQbXvkcAAAAJ&hl=zh-CN&oi=sra)<sup>1</sup>, [Shiwei Zhang](https://scholar.google.com.hk/citations?user=ZO3OQ-8AAAAJ&hl=zh-CN)<sup>2</sup>, [Changxin Gao](https://scholar.google.com.hk/citations?user=4tku-lwAAAAJ&hl=zh-CN)<sup>1</sup>, [Jiayu Wang](#)<sup>2</sup>, [Xiaoqiang Zhou](https://scholar.google.com.hk/citations?user=Z2BTkNIAAAAJ&hl=zh-CN&oi=ao)<sup>3</sup>, [Yingya Zhang](https://scholar.google.com.hk/citations?user=16RDSEUAAAAJ&hl=zh-CN)<sup>2</sup> , [Luxin Yan](#)<sup>1</sup> , [Nong Sang](https://scholar.google.com.hk/citations?user=ky_ZowEAAAAJ&hl=zh-CN)<sup>1</sup> <sup>1</sup>HUST <sup>2</sup>Alibaba Group <sup>3</sup>USTC [🎨 Project Page](https://unianimate.github.io/) <p align="middle"> <img src='https://img.alicdn.com/imgextra/i4/O1CN01bW2Y491JkHAUK4W0i_!!6000000001066-2-tps-2352-1460.png' width='784'> Demo cases generated by the proposed UniAnimate </p> </div> ## 🔥 News - **[2025/04/15]** 🔥🔥🔥🔥🔥 **We released a new model based on UniAnimate and [Wan2.1](https://github.com/Wan-Video/Wan2.1), named **UniAnimate-DiT**, including the training and inference code. Please refer to [UniAnimate-DiT](https://github.com/ali-vilab/UniAnimate-DiT) for more details.** - **[2024/07/19]** 🔥 We added a **<font color=red>noise prior</font>** to the code (refer to line 381: `noise = diffusion.q_sample(random_ref_frame.clone(), getattr(cfg, "noise_prior_value", 939), noise=noise)` in `tools/inferences/inference_unianimate_long_entrance.py`), which can help achieve better appearance preservation (such as background), especially in long video generation. In addition, we are considering releasing an upgraded version of UniAnimate if we obtain an open source license from the company. - **[2024/06/26]** For cards with large GPU memory, such as A100 GPU, we support multiple segments parallel denoising to accelerate long video inference. You can change `context_batch_size: 1` in `configs/UniAnimate_infer_long.yaml` to other values greater than 1, such as `context_batch_size: 4`. The inference speed will be improved to a certain extent. - **[2024/06/15]** 🔥🔥🔥 By offloading CLIP and VAE and explicitly adding torch.float16 (i.e., set `CPU_CLIP_VAE: True` in `configs/UniAnimate_infer.yaml`), the GPU memory can be greatly reduced. Now generating a 32x768x512 video clip only requires **~12G GPU memory**. Refer to [this issue](https://github.com/ali-vilab/UniAnimate/issues/10) for more details. Thanks to [@blackight](https://github.com/blackight) for the contribution！ - **[2024/06/13]** **🔥🔥🔥 <font color=red>We released the code and models for human image animation, enjoy it!</font>** - **[2024/06/13]** We have submitted the code to the company for approval, and **the code is expected to be released today or tomorrow**. - **[2024/06/03]** We initialized this github repository and planed to release the paper. ## TODO - [x] Release the models and inference code, and pose alignment code. - [x] Support generating both short and long videos. - [ ] Release the models for longer video generation in one batch. - [ ] Release models based on VideoLCM for faster video synthesis. - [ ] Training the models on higher resolution videos. ## Introduction <div align="center"> <p align="middle"> <img src='https://img.alicdn.com/imgextra/i3/O1CN01VvncFJ1ueRudiMOZu_!!6000000006062-2-tps-2654-1042.png' width='784'> Overall framework of UniAnimate </p> </div> Recent diffusion-based human image animation techniques have demonstrated impressive success in synthesizing videos that faithfully follow a given reference identity and a sequence of desired movement poses. Despite this, there are still two limitations: i) an extra reference model is required to align the identity image with the main video branch, which significantly inc
Excerpt of 17,916 characters
Read on GitHub
2
Shiwei Zhang · Alibaba Group
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:55392b158c035210, topic:video-generation, readme:video generation, readme:video synthesis