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.
[ICLR'25] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
| Date | Stars |
|---|---|
| 2026-07-24 | 691 |
| 2026-07-25 | 692 |
| 2026-07-28 | 693 |
| 2026-07-30 | 693 |
| 2026-08-06 | 693 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints <div align="center"> <div align="center" style="margin-top: 0px; margin-bottom: 0px;"> <img src=https://github.com/user-attachments/assets/b33c5b67-3881-4fa3-b853-f932eebc9c50 width="50%"/> </div> ### [<a href="https://arxiv.org/abs/2412.07760" target="_blank">arXiv</a>] [<a href="https://jianhongbai.github.io/SynCamMaster/" target="_blank">Project Page</a>] [<a href="https://huggingface.co/datasets/KwaiVGI/SynCamVideo-Dataset/" target="_blank">Dataset</a>] _**[Jianhong Bai<sup>1*</sup>](https://jianhongbai.github.io/), [Menghan Xia<sup>2†</sup>](https://menghanxia.github.io/), [Xintao Wang<sup>2</sup>](https://xinntao.github.io/), [Ziyang Yuan<sup>3</sup>](https://scholar.google.ru/citations?user=fWxWEzsAAAAJ&hl=en), [Xiao Fu<sup>4</sup>](https://fuxiao0719.github.io/), <br>[Zuozhu Liu<sup>1</sup>](https://person.zju.edu.cn/en/lzz), [Haoji Hu<sup>1</sup>](https://person.zju.edu.cn/en/huhaoji), [Pengfei Wan<sup>2</sup>](https://scholar.google.com/citations?user=P6MraaYAAAAJ&hl=en), [Di Zhang<sup>2</sup>](https://openreview.net/profile?id=~Di_ZHANG3)**_ <br> (*Work done during an internship at KwaiVGI, Kuaishou Technology †corresponding author) <sup>1</sup>Zhejiang University, <sup>2</sup>Kuaishou Technology, <sup>3</sup>Tsinghua University, <sup>4</sup>CUHK. **ICLR 2025** </div> **Important Note:** This open-source repository is intended to provide a reference implementation. Due to the difference in the underlying T2V model's performance, the open-source version may not achieve the same performance as the model in our paper. ## 🔥 Updates - __[2025.04.15]__: Please feel free to explore our subsequent work, [ReCamMaster](https://github.com/KwaiVGI/ReCamMaster). - __[2025.04.15]__: Update a new version of the [SynCamVideo Dataset](https://huggingface.co/datasets/KwaiVGI/SynCamVideo-Dataset). - __[2025.04.15]__: Release the [training and inference code](https://github.com/KwaiVGI/SynCamMaster?tab=readme-ov-file#%EF%B8%8F-code-syncammaster--wan21-inference--training), [model checkpoint](https://huggingface.co/KwaiVGI/SynCamMaster-Wan2.1/blob/main/step20000.ckpt). - __[2024.12.10]__: Release the [project page](https://jianhongbai.github.io/SynCamMaster/) and the [SynCamVideo Dataset](https://huggingface.co/datasets/KwaiVGI/SynCamVideo-Dataset/). ## 📖 Introduction **TL;DR:** We propose SynCamMaster, an efficient method to lift pre-trained text-to-video models for open-domain multi-camera video generation from diverse viewpoints. We also release a multi-camera synchronized video [dataset](https://huggingface.co/datasets/KwaiVGI/SynCamVideo-Dataset) rendered with Unreal Engine 5. <br> https://github.com/user-attachments/assets/1ecfaea8-5d87-4bb5-94fc-062f84bd67a1 ## ⚙️ Code: SynCamMaster + Wan2.1 (Inference & Training) The model utilized in our paper is an internally developed T2V model, not [Wan2.1](https://github.com/Wan-Video/Wan2.1). Due to company policy restrictions, we are unable to open-source the model used in the paper. Consequently, we migrated SynCamMaster to Wan2.1 to validate the effectiveness of our method. Due to differences in the underlying T2V model, you may not achieve the same results as demonstrated in the demo. ### Inference Step 1: Set up the environment [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) requires Rust and Cargo to compile extensions. You can install them using the following command: ```shell curl --proto '=https' --tlsv1.2 -sSf [https://sh.rustup.rs](https://sh.rustup.rs/) | sh . "$HOME/.cargo/env" ``` Install [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio): ```shell git clone https://github.com/KwaiVGI/SynCamMaster.git cd SynCamMaster pip install -e . ``` Step 2: Download the pretrained checkpoints 1. Download the pre-trained Wan2.1 models ```shell cd SynCamMaster python download_wan2.1.py ``` 2. Download the pre-trained SynCamMaster checkpoint Please downlo
Excerpt of 12,231 characters
Read on GitHub
Jianhong Bai
13
Xintao · Tencent · China
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:5982e901089c5a76, topic:video-generation, desc:video generation, readme:video generation