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.
[CVPR 2025] FaithDiff for Classic Film Rejuvenation, Old Photo Revival, Social Media Restoration, Image Enhancement and AIGC Enhancement.
| Date | Stars |
|---|---|
| 2026-07-24 | 261 |
| 2026-07-25 | 261 |
| 2026-07-28 | 261 |
| 2026-07-30 | 261 |
| 2026-08-06 | 261 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
### (CVPR 2025) FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolution [](https://huggingface.co/jychen9811/FaithDiff)  > [[Project Page](https://jychen9811.github.io/FaithDiff_page/)]   [[Paper](https://openaccess.thecvf.com/content/CVPR2025/papers/Chen_FaithDiff_Unleashing_Diffusion_Priors_for_Faithful_Image_Super-resolution_CVPR_2025_paper.pdf)] > [Junyang Chen](https://jychen9811.github.io/), [Jinshan Pan](https://jspan.github.io/), [Jiangxin Dong](https://scholar.google.com/citations?user=ruebFVEAAAAJ&hl=zh-CN&oi=ao) <br> > [IMAG Lab](https://imag-njust.net/), Nanjing University of Science and Technology > If FaithDiff is helpful for you, please help star the GitHub Repo. Thanks! > Welcome to visit our website (专注底层视觉领域的信息服务平台) for low-level vision: [https://lowlevelcv.com/](https://lowlevelcv.com/) --- 😊 You may also want to check our relevant works: 1. **STCDiT (CVPR 2026)** [Paper](https://arxiv.org/abs/2511.18786) | [Code](https://github.com/JyChen9811/STCDiT) A motion-aware VAE and anchor-frame-guided DiT framework enables stable video restoration, even under complex camera motions. 2. **CODSR (CVPR2026)** [Paper](https://arxiv.org/abs/2512.14061 ) | [Code](https://github.com/Chanson94/CODSR ) A one-step diffusion SR framework enabling region-discriminative activation of generative priors and precise semantic grounding. ### 🚩 **New Features/Updates** - ✅ April 3, 2025. The code has been integrated into [Diffusers](https://github.com/huggingface/diffusers/blob/main/examples/community/pipeline_faithdiff_stable_diffusion_xl.py). Respect to Eliseu Silva!!! - ✅ April 1, 2025. Supports FP8 inference and CPU offloading, significantly reducing memory usage. Thanks Eliseu Silva!!! - ✅ March 28, 2025. Update a nice gradio demo. - ✅ March 24, 2025. Release the training code. - ✅ February 09, 2025. Support ultra-high-resolution (8K and above) image restoration on 24GB GPUs. - ✅ February 08, 2025. Release [RealDeg](https://drive.google.com/file/d/1B8BaaMjXJ-1TfcTgE9MrAg8ufvaGkndP/view?usp=sharing). It includes 238 images with unknown degradations, consisting of old photographs, social media images, and classic film stills. - ✅ February 07, 2025. Release the testing code and [pre-trained model](https://huggingface.co/jychen9811/FaithDiff). - ✅ November 25, 2024. Creat the repository and the [project page](https://jychen9811.github.io/FaithDiff_page/). ### ⚡ **To do** - FaithDiff-SD3-Large - ~~Release the training code~~ - ~~Release the testing code and pre-trained model~~ --- ### 📷 Real-World Enhancement Results [<img src="figs/nezha.jpg" width="500px" height="320px"/>](https://imgsli.com/MzQ3NDQx) [<img src="figs/wukong.jpg" height="320px"/>](https://imgsli.com/MzQ3NDM5) [<img src="figs/old_photo.jpg" width="500px" height="320px"/>](https://imgsli.com/MzQ3NDYx) [<img src="figs/social_media.jpg" height="320px"/>](https://imgsli.com/MzQ3NDU2) <!--  --> --- ### 🌈 AIGC Enhancement Results [<img src="figs/pikaqiu.jpg" width="270px" height="270px"/>](https://imgsli.com/MzQ3NjEz) [<img src="figs/cat_and_snake.jpg" width="270px" height="270px"/>](https://imgsli.com/MzQ3NjAx) [<img src="figs/yangtuo.jpg" width="270px" height="270px"/>](https://imgsli.com/MzQ3NTk0) [<img src="figs/duolaameng.jpg" width="270px" height="270px"/>](https://imgsli.com/MzQ3NTk2) [<img src="figs/tiger.jpg" width="270px" height="270px"/>](https://imgsli.com/MzQ3NjA0) [<img src="figs/little_girl.jpg" width="270px" height="270px"/>](https://imgsli.com/MzQ3NjA2) [<img src="figs/boy.jpg" width="270px" height="270px"/>](https://imgsli.com/MzQ3NjE1) [<img src="figs/girl_and_cat.jpg" width="270px" height="270px"/>](https://imgsli.com/MzQ3NjA5) [<img src="figs/astronaut.jpg" width="270px" height="270px"/>](https://
Excerpt of 9,277 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:5b0fff79f593211b, topic:stable-diffusion, topic:diffusion-models, topic:super-resolution