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.
Official Repo for CVPR 2025 paper "OSDFace: One-Step Diffusion Model for Face Restoration"
| Date | Stars |
|---|---|
| 2026-07-31 | 286 |
| 2026-08-01 | 287 |
| 2026-08-06 | 287 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# OSDFace: One-Step Diffusion Model for Face Restoration [Jingkai Wang](https://github.com/jkwang28), [Jue Gong](https://github.com/gobunu), [Lin Zhang](https://github.com/wanliyungui), [Zheng Chen](https://zhengchen1999.github.io/), Xing Liu, Hong Gu, [Yutong Liu](https://isabelleliu630.github.io/), [Yulun Zhang](http://yulunzhang.com/), and [Xiaokang Yang](https://scholar.google.com/citations?user=yDEavdMAAAAJ), "One-Step Diffusion Model for Face Restoration", CVPR, 2025 [](https://www.jingkaiwang.com/OSDFace/) [](https://arxiv.org/abs/2411.17163) [](https://github.com/jkwang28/OSDFace/releases/download/v2/supp.pdf) [](https://github.com/jkwang28/OSDFace/releases) [](https://github.com/jkwang28/OSDFace) [](https://github.com/jkwang28/OSDFace) #### 🔥🔥🔥 News - **2025-12-23:** Inference code and pretrained models are released. - **2025-04-23:** Results are released. (Synthetic dataset: CelebA-Test; Real-world datasets: Wider-Test, LFW-Test, and WebPhoto-Test) - **2025-02-27:** Congratulations! OSDFace is accepted to CVPR 2025. - **2024-11-25:** This repo is released. --- > **Abstract:** Diffusion models have demonstrated impressive performance in face restoration. Yet, their multi-step inference process remains computationally intensive, limiting their applicability in real-world scenarios. Moreover, existing methods often struggle to generate face images that are harmonious, realistic, and consistent with the subject’s identity. In this work, we propose OSDFace, a novel one-step diffusion model for face restoration. Specifically, we propose a visual representation embedder (VRE) to better capture prior information and understand the input face. In VRE, low-quality faces are processed by a visual tokenizer and subsequently embedded with a vector-quantized dictionary to generate visual prompts. Additionally, we incorporate a facial identity loss derived from face recognition to further ensure identity consistency. We further employ a generative adversarial network (GAN) as a guidance model to encourage distribution alignment between the restored face and the ground truth. Experimental results demonstrate that OSDFace surpasses current state-of-the-art (SOTA) methods in both visual quality and quantitative metrics, generating high-fidelity, natural face images with high identity consistency.  --- <!--  --> [<img src="assets/images/CAT-0012.png" height="200"/>](https://imgsli.com/MzIxNTU3) [<img src="assets/images/CAT-0051.png" height="200"/>](https://imgsli.com/MzIxNTU5) [<img src="assets/images/CAT-0054.png" height="200"/>](https://imgsli.com/MzIxNTYw) [<img src="assets/images/CAT-1093.png" height="200"/>](https://imgsli.com/MzIxNTYy) [<img src="assets/images/LFW_Abdullatif_Sener.png" height="200"/>](https://imgsli.com/MzIxNTYz) [<img src="assets/images/WebPhoto_0101.png" height="200"/>](https://imgsli.com/MzIxNTY4) [<img src="assets/images/WT_0011.png" height="200"/>](https://imgsli.com/MzIxNTY5) [<img src="assets/images/WT_0000.png" height="200"/>](https://imgsli.com/MzIxNTcz) --- ## ⚒️ TODO * [x] Release inference code and pretrained models * [ ] Release training code ## 🔗 Contents - [x] [Environment](#datasets) - [x] [Datasets](#datasets) - [x] [Models](https://sjtueducn-my.sharepoint.com/:f:/g/personal/jingkaiwang_sjtu_edu_cn/EhIFpGRj6GxLoHG54TyeMT0Bg0wkiDHCcZ4B674k9veCiA?e=zQYHze) - [x] [Inference](#Inference) - [ ] Training - [x] [Results](#result
Excerpt of 9,926 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:731a4f40568ef9b9, desc:diffusion model