Top AI Repos โ 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.
InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation ๐ฅ
| Date | Stars |
|---|---|
| 2026-07-31 | 2012 |
| 2026-08-02 | 2012 |
| 2026-08-06 | 2012 |
| 2026-08-12 | 2016 |
| 2026-08-18 | 2015 |
| 2026-08-22 | 2016 |
| 2026-08-25 | 2017 |
| 2026-08-27 | 2018 |
| 2026-08-31 | 2017 |
| 2026-09-02 | 2018 |
| 2026-09-04 | 2017 |
| 2026-09-07 | 2015 |
| 2026-09-09 | 2016 |
| 2026-09-10 | 2017 |
| 2026-09-15 | 2018 |
| 2026-09-20 | 2018 |
Today
โ stars today
This week
+1 stars this week
This month
+3 stars this month
Momentum
0.0
growth rate 0.05%/day
<div align="center"> <h1>InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation</h1> [**Haofan Wang**](https://haofanwang.github.io/)<sup>*</sup> ยท [**Matteo Spinelli**](https://github.com/cubiq) ยท [**Qixun Wang**](https://github.com/wangqixun) ยท [**Xu Bai**](https://huggingface.co/baymin0220) ยท [**Zekui Qin**](https://github.com/ZekuiQin) ยท [**Anthony Chen**](https://antonioo-c.github.io/) InstantX Team <sup>*</sup>corresponding authors <a href='https://instantstyle.github.io/'><img src='https://img.shields.io/badge/Project-Page-green'></a> <a href='https://arxiv.org/abs/2404.02733'><img src='https://img.shields.io/badge/Technique-Report-red'></a> [](https://huggingface.co/spaces/InstantX/InstantStyle) [](https://modelscope.cn/studios/instantx/InstantStyle/summary) [](https://github.com/InstantStyle/InstantStyle) </div> InstantStyle is a general framework that employs two straightforward yet potent techniques for achieving an effective disentanglement of style and content from reference images. <!-- <img src='assets/pipe.png'> --> <div align="center"> <img src='assets/page0.png' width = 900 > </div> ## Principle Separating Content from Image. Benefit from the good characterization of CLIP global features, after subtracting the content text fea- tures from the image features, the style and content can be explicitly decoupled. Although simple, this strategy is quite effective in mitigating content leakage. <p align="center"> <img src="assets/subtraction.png"> </p> Injecting into Style Blocks Only. Empirically, each layer of a deep network captures different semantic information the key observation in our work is that there exists two specific attention layers handling style. Specifically, we find up blocks.0.attentions.1 and down blocks.2.attentions.1 capture style (color, material, atmosphere) and spatial layout (structure, composition) respectively. <p align="center"> <img src="assets/tree.png"> </p> ## Release - [2024/07/06] ๐ฅ We release [CSGO](https://github.com/instantX-research/CSGO) page for content-style composition. Code will be released soon. - [2024/07/01] ๐ฅ We release [InstantStyle-Plus](https://instantstyle-plus.github.io/) report for content preserving. - [2024/04/29] ๐ฅ We support InstantStyle natively in diffusers, usage can be found [here](https://github.com/InstantStyle/InstantStyle?tab=readme-ov-file#use-in-diffusers) - [2024/04/24] ๐ฅ InstantStyle for fast generation, find demos at [InstantStyle-SDXL-Lightning](https://huggingface.co/spaces/radames/InstantStyle-SDXL-Lightning) and [InstantStyle-Hyper-SDXL](https://huggingface.co/spaces/radames/InstantStyle-Hyper-SDXL). - [2024/04/24] ๐ฅ We support [HiDiffusion](https://github.com/megvii-research/HiDiffusion) for generating highres images, find more information [here](https://github.com/InstantStyle/InstantStyle/tree/main?tab=readme-ov-file#high-resolution-generation). - [2024/04/23] ๐ฅ InstantStyle has been natively supported in diffusers, more information can be found [here](https://github.com/huggingface/diffusers/pull/7668). - [2024/04/20] ๐ฅ InstantStyle is supported in [Mikubill/sd-webui-controlnet](https://github.com/Mikubill/sd-webui-controlnet/discussions/2770). - [2024/04/11] ๐ฅ We add the experimental distributed inference feature. Check it [here](https://github.com/InstantStyle/InstantStyle?tab=readme-ov-file#distributed-inference). - [2024/04/10] ๐ฅ We support an [online demo](https://modelscope.cn/studios/instantx/InstantStyle/summary) on ModelScope. - [2024/04/09] ๐ฅ We support an [online demo](https://huggingface.co/spaces/InstantX/InstantStyle) on Huggingface. - [2024/04/09] ๐ฅ We support SDXL-inpainting, more information can be found [here](https://github.com/Instant
Excerpt of 16,367 characters
Read on GitHub
55
Ameer Azam ยท AICSC ยท India
10
Max Ku ยท โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ
5
3
3
Rupesh Sreeraman ยท India
2
2
Faych
1
Sam Gao ยท DINQ ยท China
1
Frank (Haofan) Wang
1
Would you bet a product on this? Bounded 0โ100 and slow moving.
matched fp:db0e489d1576fbab, desc:text-to-image, desc:image generation