xinntao /Real-ESRGAN

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

★ 37,508⑂ 4,537👁 257⑃ 131● 769▤ 10
PythonBSD-3-ClauseCreated 2021-07-19
Download: Real-ESRGAN v0.3.0 Release NoteReal-ESRGAN-0.3.0 ↓0.3.02022-09-20
+11
Daily
+93
Weekly
37,508
stars
4,537
forks
257
watchers
131
prs
769
issues
10
releases

README

English | 简体中文



👀Demos | 🚩Updates | ⚡Usage | 🏰Model Zoo | 🔧Install  | 💻Train | ❓FAQ | 🎨Contribution











🔥 AnimeVideo-v3 model (动漫视频小模型). Please see [anime video models] and [comparisons]
🔥 RealESRGAN_x4plus_anime_6B for anime images (动漫插图模型). Please see [anime_model]


1. :boom: Update online Replicate demo: 
1. Online Colab demo for Real-ESRGAN:  | Online Colab demo for for Real-ESRGAN (anime videos): 
1. Portable Windows / Linux / MacOS executable files for Intel/AMD/Nvidia GPU. You can find more information here. The ncnn implementation is in Real-ESRGAN-ncnn-vulkan


Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
We extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data.

🌌 Thanks for your valuable feedbacks/suggestions. All the feedbacks are updated in feedback.md.

---

If Real-ESRGAN is helpful, please help to ⭐ this repo or recommend it to your friends 😊 
Other recommended projects:
▶️ GFPGAN: A practical algorithm for real-world face restoration 
▶️ BasicSR: An open-source image and video restoration toolbox
▶️ facexlib: A collection that provides useful face-relation functions.
▶️ HandyView: A PyQt5-based image viewer that is handy for view and comparison 
▶️ HandyFigure: Open source of paper figures 

---

 📖 Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

 [Paper]   [YouTube Video]   [B站讲解]   [Poster]   [PPT slides]
 Xintao Wang, Liangbin Xie, Chao Dong, Ying Shan 
 Tencent ARC Lab; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences


  


---


 🚩 Updates

- ✅ Add the realesr-general-x4v3 model - a tiny small model for general scenes. It also supports the -dn option to balance the noise (avoiding over-smooth results). -dn is short for denoising strength.
- ✅ Update the RealESRGAN AnimeVideo-v3 model. Please see anime video models and comparisons for more details.
- ✅ Add small models for anime videos. More details are in anime video models.
- ✅ Add the ncnn implementation Real-ESRGAN-ncnn-vulkan.
- ✅ Add RealESRGAN_x4plus_anime_6B.pth, which is optimized for anime images with much smaller model size. More details and comparisons with waifu2x are in anime_model.md
- ✅ Support finetuning on your own data or paired data (i.e., finetuning ESRGAN). See here
- ✅ Integrate GFPGAN to support face enhancement.
- ✅ Integrated to Huggingface Spaces with Gradio. See Gradio Web Demo. Thanks @AK391
- ✅ Support arbitrary scale with --outscale (It actually further resizes outputs with LANCZOS4). Add RealESRGAN_x2plus.pth model.
- ✅ The inference code supports: 1) tile options; 2) images with alpha channel; 3) gray images; 4) 16-bit images.
- ✅ The training codes have been released. A detailed guide can be found in Training.md.

---


 👀 Demos Videos

 Bilibili

- 大闹天宫片段
- Anime dance cut 动漫魔性舞蹈
- 海贼王片段

 YouTube

 🔧 Dependencies and Installation

- Py

Top issues

Discussions

Latest release

Real-ESRGAN v0.3.0 Release Note v0.3.0 2022-09-20
🚀 Long time no see ☄️

✨ Highlights

✅ add realesr-general-x4v3 and realesr-general-wdn-x4v3. They are very tiny models for general scenes, and they may more robust. But as they are tiny models, their performance may be limited.
✅ support denoise strength for realesr-general-x4v3. You can use the -dn option to adjust the denising strength. Denoise strength. 0 for weak denoise (keep noise), 1 for strong denoise ability. Only used for the realesr-general-x4v3 model.
✅ update inference_video: support auto download. You do not need to download models explicitly. If the models are not downloa

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON