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.
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
| Date | Stars |
|---|---|
| 2026-07-31 | 1934 |
| 2026-08-03 | 1934 |
| 2026-08-06 | 1934 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center"> <img src="asset/logo-sigma.png" height=120> </p> ### <div align="center">👉 PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation<div> <div align="center"> <a href="https://pixart-alpha.github.io/PixArt-sigma-project/"><img src="https://img.shields.io/static/v1?label=Project%20Page&message=Github&color=blue&logo=github-pages"></a>   <a href="https://arxiv.org/abs/2403.04692"><img src="https://img.shields.io/static/v1?label=Paper&message=Arxiv:Sigma&color=red&logo=arxiv"></a>   <a href="https://huggingface.co/spaces/PixArt-alpha/PixArt-Sigma"><img src="https://img.shields.io/static/v1?label=Demo&message=HuggingFace&color=yellow"></a>   <a href="https://discord.gg/rde6eaE5Ta"><img src="https://img.shields.io/static/v1?label=Discuss&message=Discord&color=purple&logo=discord"></a>   </div> --- This repo contains PyTorch model definitions, pre-trained weights and inference/sampling code for our paper exploring Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation. You can find more visualizations on our [project page](https://pixart-alpha.github.io/PixArt-sigma-project/). > [**PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation**](https://github.com/PixArt-alpha/PixArt-sigma)<br> > [Junsong Chen*](https://lawrence-cj.github.io/), [Chongjian Ge*](https://chongjiange.github.io/), > [Enze Xie*](https://xieenze.github.io/)†, > [Yue Wu*](https://yuewuhkust.github.io/), > [Lewei Yao](https://scholar.google.com/citations?user=hqDyTg8AAAAJ&hl=zh-CN&oi=ao), > [Xiaozhe Ren](https://scholar.google.com/citations?user=3t2j87YAAAAJ&hl=en), [Zhongdao Wang](https://zhongdao.github.io/), > [Ping Luo](http://luoping.me/), > [Huchuan Lu](https://scholar.google.com/citations?hl=en&user=D3nE0agAAAAJ), > [Zhenguo Li](https://scholar.google.com/citations?user=XboZC1AAAAAJ) > <br>Huawei Noah’s Ark Lab, DLUT, HKU, HKUST<br> --- ## Welcome everyone to contribute🔥🔥!! Learning from the previous [PixArt-α](https://github.com/PixArt-alpha/PixArt-alpha) project, we will try to keep this repo as simple as possible so that everyone in the PixArt community can use it. --- ## Breaking News 🔥🔥!! - (🔥 New) Apr. 24, 2024. 💥 [🧨 diffusers](https://github.com/huggingface/diffusers/pull/7654) support us now! Congrats!🎉. Remember to update your [diffusers checkpoint](https://huggingface.co/PixArt-alpha/PixArt-Sigma-XL-2-2K-MS/tree/main/transformer) once to make it available. - (🔥 New) Apr. 24, 2024. 💥 [LoRA code](asset/docs/pixart_lora.md) is released!! - (✅ New) Apr. 23, 2024. 💥 [PixArt-Σ 2K ckpt](#12-download-pretrained-checkpoint) is released!! - (✅ New) Apr. 16, 2024. 💥 [PixArt-Σ Online Demo](https://huggingface.co/spaces/PixArt-alpha/PixArt-Sigma) is available!! - (✅ New) Apr. 16, 2024. 💥 PixArt-α-DMD One Step Generator [training code](asset/docs/pixart_dmd.md) are all released! - (✅ New) Apr. 11, 2024. 💥 [PixArt-Σ Demo](#3-pixart-demo) & [PixArt-Σ Pipeline](#2-integration-in-diffusers)! PixArt-Σ supports `🧨 diffusers` using [patches](scripts/diffusers_patches.py) for fast experience! - (✅ New) Apr. 10, 2024. 💥 PixArt-α-DMD one step sampler [demo code](app/app_pixart_dmd.py) & [PixArt-α-DMD checkpoint](https://huggingface.co/PixArt-alpha/PixArt-Alpha-DMD-XL-2-512x512) 512px are released! - (✅ New) Apr. 9, 2024. 💥 [PixArt-Σ checkpoint](https://huggingface.co/PixArt-alpha/PixArt-Sigma/blob/main/PixArt-Sigma-XL-2-1024-MS.pth) 1024px is released! - (✅ New) Apr. 6, 2024. 💥 [PixArt-Σ checkpoint](https://huggingface.co/PixArt-alpha/PixArt-Sigma/tree/main) 256px & 512px are released! - (✅ New) Mar. 29, 2024. 💥 [PixArt-Σ](https://pixart-alpha.github.io/PixArt-sigma-project/) training & inference code & toy data are released!!! --- ## Contents -Main * [Weak-to-Strong](#-compare-with-pixart-α) * [Training](#-how-to-train) * [Inference](#-how-to-test) * [Use diffusers](#2-integration-in-dif
Excerpt of 17,813 characters
Read on GitHub
Junsong Chen · NVIDIA Research, HKU · Hong Kong
38
13
7
LoveSy · Zhejiang University · Hong Kong
1
Enze Xie · NVIDIA · United States
1
Raul Ciotescu
1
1
7sunarni
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:cfd0778ccf81752d, desc:text-to-image, desc:image generation