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 2025] Autoregressive Video Generation without Vector Quantization
| Date | Stars |
|---|---|
| 2026-07-24 | 656 |
| 2026-07-25 | 656 |
| 2026-07-28 | 657 |
| 2026-07-30 | 657 |
| 2026-08-06 | 657 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <h1>Autoregressive Video Generation without Vector Quantization</h1> <p align="center"> <a href="https://arxiv.org/abs/2412.14169"><img src="https://img.shields.io/badge/ArXiv-2512.14169-%23840707.svg" alt="ArXiv"></a> <a href="https://huggingface.co/spaces/BAAI/nova-d48w1024-sdxl1024"><img src="https://img.shields.io/badge/🤗 Demo-T2I-%26840707.svg" alt="T2IDemo"></a> <a href="https://huggingface.co/spaces/BAAI/nova-d48w1024-osp480"><img src="https://img.shields.io/badge/🤗 Demo-T2V-%26840707.svg" alt="T2VDemo"></a> <a href="http://bitterdhg.github.io/NOVA_page"><img src="https://img.shields.io/badge/Webpage-NOVA-%237CB4F7.svg" alt="Webpage"></a> </p> [Haoge Deng](https://scholar.google.com/citations?user=S2sbvjgAAAAJ&hl=zh-CN&oi=ao)<sup>1,4*</sup>, [Ting Pan](https://scholar.google.com/citations?&user=qQv6YbsAAAAJ)<sup>2,4*</sup>, [Haiwen Diao](https://scholar.google.com/citations?user=46eCjHQAAAAJ&hl=zh-CN)<sup>3,4*</sup>, [Zhengxiong Luo](https://scholar.google.com/citations?user=Sz1yTZsAAAAJ&hl=zh-CN)<sup>4*</sup>, [Yufeng Cui](https://scholar.google.com/citations?user=5Ydha2EAAAAJ&hl=zh-CN)<sup>4</sup><br> [Huchuan Lu](https://scholar.google.com/citations?user=D3nE0agAAAAJ&hl=zh-CN)<sup>3</sup>, [Shiguang Shan](https://scholar.google.com/citations?user=Vkzd7MIAAAAJ&hl=en)<sup>2</sup>, [Yonggang Qi](https://scholar.google.com.tw/citations?user=pQNpf7cAAAAJ&hl=zh-CN&oi=ao)<sup>1†</sup>, [Xinlong Wang](https://scholar.google.com/citations?user=DPz0DjYAAAAJ&hl=zh-CN)<sup>4†</sup><br> [BUPT](https://www.bupt.edu.cn)<sup>1</sup>, [ICT-CAS](http://english.ict.cas.cn)<sup>2</sup>, [DLUT](https://en.dlut.edu.cn)<sup>3</sup>, [BAAI](https://www.baai.ac.cn/en)<sup>4</sup><br> <sup>*</sup> Equal Contribution, <sup>†</sup> Corresponding Author <br><br><image src="assets/model_overview.png"/> </div> We present **NOVA** (**NO**n-Quantized **V**ideo **A**utoregressive Model), a model that enables autoregressive image/video generation with high efficiency. **NOVA** reformulates the video generation problem as non-quantized autoregressive modeling of temporal *frame-by-frame* prediction and spatial *set-by-set* prediction. **NOVA** generalizes well and enables diverse zero-shot generation abilities in one unified model. ## 🚀News - ```[Oct 2025]``` Released our next video generation model 🐻 [URSA](https://github.com/baaivision/URSA). - ```[Jul 2025]``` Codebase refactor with **Accelerate**, **OmegaConf** and **Wandb**. - ```[Feb 2025]``` Released [Evaluation Guide](./docs/evaluation.md). - ```[Feb 2025]``` Released [Training Guide](./docs/training.md) - ```[Jan 2025]``` Accepted by ICLR 2025. [[OpenReview]](https://openreview.net/forum?id=JE9tCwe3lp) & [[Poster]](https://iclr.cc/virtual/2025/poster/30117). - ```[Dec 2024]``` Released [Project Page](http://bitterdhg.github.io/NOVA_page) - ```[Dec 2024]``` Released 🤗 Online Demo (<a href="https://huggingface.co/spaces/BAAI/nova-d48w1024-sdxl1024"><b>T2I</b></a>, <a href="https://huggingface.co/spaces/BAAI/nova-d48w1024-osp480"><b>T2V</b></a>) - ```[Dec 2024]``` Released [paper](https://arxiv.org/abs/2412.14169), [weights](#model-zoo), and [Quick Start](#2-quick-start) guide and Gradio Demo [local code](#3-gradio-demo) . ## ✨Hightlights - 🔥 **Novel Approach**: Non-quantized video autoregressive generation. - 🔥 **State-of-the-art Performance**: High efficiency with state-of-the-art t2i/t2v results. - 🔥 **Unified Modeling**: Multi-task capabilities in a single unified model. ## 🗄️Model Zoo <a id="model-zoo"></a> > See detailed description in [Model Zoo](./docs/model_zoo.md) ### Text to Image <a id="text-to-image-weight"></a> | Model | Parameters | Resolution | Data | Weight | GenEval | DPGBench | |:-----------:|:----------:|:----------:|:----:|:---------------------------------------------------------------------:|:--------:|:-------:| | NOVA-0.6B | 0.6B | 512x512 | 16M | [🤗 HF link](h
Excerpt of 10,907 characters
Read on GitHub
67
8
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:fa471c15eee9b85d, topic:diffusion-models, topic:image-generation, readme:text-to-image
matched fp:fa471c15eee9b85d, topic:video-generation, desc:video generation, readme:video generation