BSRGAN

Practical image super-resolution model trained on diverse degradations.

Open SourceSelf HostedOffline CapableGPU Required (4GB+ VRAM)
0.0 (0)

About

BSRGAN from the Computer Vision Lab at ETH Zurich is a practical image super-resolution model trained with a degradation pipeline that randomly combines blur, noise, JPEG compression, and resizing, so it generalizes to real-world low-quality images better than models trained on simple synthetic downsampling. It includes training and test code and pretrained weights. Released under the Apache 2.0 license.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Easy (2/5)
License
Apache-2.0
Minimum VRAM
4 GB
Added
Apr 3, 2026

Related Tools

Image restoration using Swin Transformer for super-resolution and denoising.

Open SourceSelf HostedOfflineGPU 4GB+
Intermediate
0.0 (0)

AI-powered image inpainting tool for removing objects and defects from photos.

Open SourceSelf HostedOffline
Beginner
0.0 (0)

Modular Stable Diffusion web UI focused on power users and server deployment.

Open SourceSelf HostedOfflineGPU 6GB+
Easy
0.0 (0)

Face restoration model by Tencent ARC for enhancing old or low-quality face photos.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)

Optimized fork of AUTOMATIC1111 with better memory management and speed.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)

Robust face restoration using codebook lookup transformer.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)
Browse all AI Image/Video Editing tools