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) Adversarial Diffusion Compression for Real-World Image Super-Resolution [PyTorch]
| Date | Stars |
|---|---|
| 2026-07-30 | 283 |
| 2026-08-11 | 284 |
| 2026-08-18 | 285 |
| 2026-08-21 | 284 |
| 2026-08-27 | 286 |
| 2026-08-28 | 287 |
| 2026-08-29 | 287 |
| 2026-09-08 | 289 |
| 2026-09-11 | 290 |
| 2026-09-15 | 291 |
| 2026-09-17 | 292 |
| 2026-10-25 | 293 |
| 2026-10-27 | 293 |
| 2026-10-28 | 294 |
| 2026-10-29 | 294 |
| 2026-11-04 | 294 |
Today
— stars today
This week
— stars this week
This month
+2 stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center"> <img src="assets/icon.png" alt="icon" width="200px"/> </p> # (CVPR 2025) Adversarial Diffusion Compression for Real-World Image Super-Resolution [PyTorch] [](https://arxiv.org/abs/2411.13383) [](https://huggingface.co/Guaishou74851/AdcSR)  [Bin Chen](https://scholar.google.com/citations?user=aZDNm98AAAAJ)<sup>1,3,\*</sup> | [Gehui Li](https://github.com/cvsym)<sup>1,\*</sup> | [Rongyuan Wu](https://scholar.google.com/citations?user=A-U8zE8AAAAJ)<sup>2,3,\*</sup> | [Xindong Zhang](https://scholar.google.com/citations?user=q76RnqIAAAAJ)<sup>3</sup> | [Jie Chen](https://aimia-pku.github.io/)<sup>1,†</sup> | [Jian Zhang](https://jianzhang.tech/)<sup>1,†</sup> | [Lei Zhang](https://www4.comp.polyu.edu.hk/~cslzhang/)<sup>2,3</sup> <sup>1</sup> *School of Electronic and Computer Engineering, Peking University* <sup>2</sup> *The Hong Kong Polytechnic University*, <sup>3</sup> *OPPO Research Institute* <sup>*</sup> Equal Contribution. <sup>†</sup> Corresponding Authors. ⭐ **If AdcSR is helpful to you, please star this repo. Thanks!** 🤗 ## 📝 Overview ### Highlights - **Adversarial Diffusion Compression (ADC).** We remove and prune redundant modules from the one-step diffusion network [OSEDiff](https://github.com/cswry/OSEDiff) and apply adversarial distillation to retain generative capabilities despite reduced capacity. - **Real-Time [Stable Diffusion](https://huggingface.co/stabilityai/stable-diffusion-2-1)-Based Image Super-Resolution.** AdcSR super-resolves a 128×128 image to 512×512 **in just 0.03s 🚀** on an A100 GPU. - **Competitive Visual Quality.** Despite **74% fewer parameters 📉** than [OSEDiff](https://github.com/cswry/OSEDiff), AdcSR achieves **competitive image quality** across multiple benchmarks. ### Framework 1. **Structural Compression** - **Removable modules** (VAE encoder, text prompt extractor, cross-attention, time embeddings) are eliminated. - **Prunable modules** (UNet, VAE decoder) are **channel-pruned** to optimize efficiency while preserving performance. <p align="center"> <img src="assets/teaser.png" alt="teaser" width="55%"/> </p> 2. **Two-Stage Training** 1. **Pretraining a Pruned VAE Decoder** to maintain its ability to decode latent representations. 2. **Adversarial Distillation** to align compressed network features with the teacher model (e.g., [OSEDiff](https://github.com/cswry/OSEDiff)) and ground truth images. <p align="center"> <img src="assets/method.png" alt="method" /> </p> ## 😍 Visual Results [<img src="assets/demo1.png" height="240px"/>](https://imgsli.com/MzU2MjU1) [<img src="assets/demo2.png" height="240px"/>](https://imgsli.com/MzU2MjU2) [<img src="assets/demo3.png" height="240px"/>](https://imgsli.com/MzU2MjU3) [<img src="assets/demo4.png" height="242px"/>](https://imgsli.com/MzU2NTg4) [<img src="assets/demo5.png" height="242px"/>](https://imgsli.com/MzU2NTkw) [<img src="assets/demo6.png" height="242px"/>](https://imgsli.com/MzU2NTk1) [<img src="assets/demo7.png" height="319px"/>](https://imgsli.com/MzU2OTE0) [<img src="assets/demo8.png" height="319px"/>](https://imgsli.com/MzU2OTE1) https://github.com/user-attachments/assets/1211cefa-8704-47f5-82cd-ec4ef084b9ec <img src="assets/comp.png" alt="comp" width="840px" /> ## ⚙ Installation ```shell git clone https://github.com/Guaishou74851/AdcSR.git cd AdcSR conda create -n AdcSR python=3.10 conda activate AdcSR pip install --upgrade pip pip install -r requirements.txt chmod +x train.sh train_debug.sh test_debug.sh evaluate_debug.sh ``` ## ⚡ Test 1. **Download test datasets** (`DIV2K-Val.zip`, `DRealSR.zip`, `RealSR.zip`) from [Hugging Face](https://huggingface.co/Guaishou74851/AdcSR) or [PKU Disk](https://disk.pku.edu.cn/link/AAD499197CBF054392BC406
Excerpt of 6,922 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:7a8eb952f658b0c2, topic:diffusion-models, topic:super-resolution, readme:stable diffusion
matched fp:7a8eb952f658b0c2, topic:deep-learning, topic:pytorch, readme:pretraining