Collections

Restore images

These models restore and improve images by fixing defects like blur, noise, and low resolution. Key capabilities:

  • Deblurring - Sharpen blurry images by reversing blur effects. Useful for old photos.
  • Denoising - Remove grain and artifacts by learning noise patterns.
  • Colorization - Add realistic color to black and white photos.
  • Face restoration - Improve the image quality of faces in old photos, or unrealistic AI generated faces.

Our Picks

Best restoration model: google-research/maxim

If you need to sharpen a blurry photo, or remove noise or compression artifacts, start with google-research/maxim. It has a total of 11 image restoration models baked-in that let you deblur, denoise, remove raindrops, and more. If you’re not getting the results you’re looking for, try megvii-research/nafnet which is similar but supports fewer restoration features.

Best colorization model: piddnad/ddcolor

The best model for adding color to black and white photos is piddnad/ddcolor, which was released in 2023. If you are looking for more saturated results try out arielreplicate/deoldify_image.

Best face restoration model: sczhou/codeformer

If you’re looking for a face restoration model, try starting with sczhou/codeformer. It produces more realistic faces than alternatives like tencentarc/gfpgan. If you aren’t getting the exact image improvements you want, we recommend exploring more modern upscaling models like batouresearch/magic-image-refiner.

Recommended models

tencentarc / gfpgan

Practical face restoration algorithm for *old photos* or *AI-generated faces*

82.2M runs

sczhou / codeformer

Robust face restoration algorithm for old photos / AI-generated faces

36.1M runs

jingyunliang / swinir

Image Restoration Using Swin Transformer

5.8M runs

megvii-research / nafnet

Nonlinear Activation Free Network for Image Restoration

1.3M runs

microsoft / bringing-old-photos-back-to-life

Bringing Old Photos Back to Life

933.1K runs

cjwbw / bigcolor

Colorization using a Generative Color Prior for Natural Images

515K runs

google-research / maxim

Multi-Axis MLP for Image Processing

472.9K runs

arielreplicate / deoldify_​image

Add colours to old images

403K runs

tencentarc / vqfr

Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

176K runs

yangxy / gpen

Blind Face Restoration in the Wild

161.6K runs

cjwbw / supir

Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild. This version uses LLaVA-13b for captioning.

155K runs

piddnad / ddcolor

Towards Photo-Realistic Image Colorization via Dual Decoders

150.2K runs

cjwbw / vqfr

Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

139.6K runs

codeslake / ifan-defocus-deblur

Removes defocus blur in an image

118.2K runs

cjwbw / night-enhancement

Unsupervised Night Image Enhancement

41.3K runs

batouresearch / magic-style-transfer

Restyle an image with the style of another one. I strongly suggest to upscale the results with Clarity AI

16.6K runs

cjwbw / supir-v0f

Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild. This is the SUPIR-v0F model and does NOT use LLaVA-13b.

10.2K runs

mv-lab / instructir

High-Quality Image Restoration Following Human Instructions

9.9K runs

cjwbw / supir-v0q

Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild. This is the SUPIR-v0Q model and does NOT use LLaVA-13b.

7.2K runs

codeplugtech / object_​remover

3.6K runs