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 & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.
| Date | Stars |
|---|---|
| 2026-07-24 | 1964 |
| 2026-07-25 | 1964 |
| 2026-07-28 | 1964 |
| 2026-07-30 | 1964 |
| 2026-08-06 | 1964 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <br> <img src="docs/showo_title.png" width="200"> <h3>One Single Transformer to Unify Multimodal Understanding and Generation</h3> [Jinheng Xie](https://sierkinhane.github.io/)<sup>1*</sup> [Weijia Mao](https://scholar.google.com/citations?hl=zh-CN&user=S7bGBmkyNtEC&view_op=list_works&sortby=pubdate)<sup>1*</sup> [Zechen Bai](https://www.baizechen.site/)<sup>1*</sup> [David Junhao Zhang](https://junhaozhang98.github.io/)<sup>1*</sup> <br> Weihao Wang<sup>2</sup> [Kevin Qinghong Lin](https://qinghonglin.github.io/)<sup>1</sup> [Yuchao Gu](https://ycgu.site/)<sup>1</sup> Zhijie Chen<sup>2</sup> [Zhenheng Yang](https://scholar.google.com/citations?user=Ds5wwRoAAAAJ&hl=en)<sup>2</sup> [Mike Zheng Shou](https://sites.google.com/view/showlab)<sup>1</sup> <sup>1</sup> [Show Lab](https://sites.google.com/view/showlab/home?authuser=0), National University of Singapore <sup>2</sup> Bytedance [](https://openreview.net/pdf?id=o6Ynz6OIQ6) [](https://arxiv.org/pdf/2408.12528) [](https://huggingface.co/spaces/showlab/Show-o) [](https://discord.gg/p6k7XupM) [](https://github.com/showlab/Show-o/blob/main/docs/wechat_qa_3.jpg) </div> [//]: # ([](https://hits.seeyoufarm.com)) <div align="center"> <br> <img src="show-o2/docs/showo2.png" width="200"> <h3>Improved Native Unified Multimodal Models</h3> [Jinheng Xie](https://sierkinhane.github.io/)<sup>1</sup> [Zhenheng Yang](https://scholar.google.com/citations?user=Ds5wwRoAAAAJ&hl=en)<sup>2</sup> [Mike Zheng Shou](https://sites.google.com/view/showlab)<sup>1</sup> <sup>1</sup> [Show Lab](https://sites.google.com/view/showlab/home?authuser=0), National University of Singapore <sup>2</sup> Bytedance [](https://arxiv.org/abs/2506.15564) [](https://github.com/showlab/Show-o/tree/main/show-o2) [](https://github.com/showlab/Show-o/blob/main/docs/wechat_qa_3.jpg) </div> ## News * **[2025-09-18]** [Arxiv update](https://arxiv.org/pdf/2506.15564) to include video understanding, OneIG, and more ablation study results. * **[2025-09-18]** **Show-o2 has been accepted to NeurIPS 2025.** * **[2025-09-05]** Release the 1.5B and 7B models with video understanding capability. * **[2025-07-05]** **Fix some issues related to visualization of generated images during training.** * **[2025-07-05]** We release the training and inference code for simple mixed-modality generation. * **[2025-06-27]** We release the training code for multimodal understanding and generation. * **[2025-06-25]** We thank team [OneIG-Bench](https://github.com/OneIG-Bench/OneIG-Benchmark) for evaluating Show-o2 models on their new benchmark, in which our models have achieved leading performance in terms of Alignment and Reasoning metrics. The leaderboard is maintained [here](https://oneig-bench.github.io/). <img src="show-o2/docs/OnelG-Bench.jpg" width="1000"> * **[2025-06-20]** We are including more concurrent works in our [comparative analysis tables](https://github.com/showlab/Show-o/blob/main/show-o2/docs/comparative_analysis.png). Feel free to reach out to us if we miss your works. [//]: # (<img src="show-o2/docs/comparative_
Excerpt of 18,901 characters
Read on GitHub
206
17
6
5
4
HuggingFace · Belgium
1
1
Kevin · Department of Engineering Science, University of Oxford · United Kingdom
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4c86d0c774eca354, topic:multimodal, desc:multimodal, readme:multimodal
matched fp:4c86d0c774eca354, topic:large-language-models
matched fp:4c86d0c774eca354, topic:diffusion-models