iceclear / stablesr

Exploiting Diffusion Prior for Real-World Image Super-Resolution

  • Public
  • 5.1K runs
  • A100 (80GB)
  • GitHub
  • Paper
  • License
Iterate in playground

Input

input_image
*file

Input image

integer

Number of DDPM steps for sampling

Default: 200

number

Balance the quality (lower number) and fidelity (higher number)

Default: 0.5

number

The upscale for super-resolution, 4x SR by default

Default: 4

integer
(minimum: 0, maximum: 64)

The overlap between tiles, betwwen 0 to 64

Default: 32

string

An enumeration.

Default: "adain"

integer

Random seed. Leave blank to randomize the seed

Output

output
Generated in

Run time and cost

This model costs approximately $0.10 to run on Replicate, or 10 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 75 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Exploiting Diffusion Prior for Real-World Image Super-Resolution

Demo on 4K Results

  • StableSR is capable of achieving arbitrary upscaling in theory, below is a 8x example with a result beyond 4K (5120x3680).

Citation

If our work is useful for your research, please consider citing:

@article{wang2024exploiting,
  author = {Wang, Jianyi and Yue, Zongsheng and Zhou, Shangchen and Chan, Kelvin C.K. and Loy, Chen Change},
  title = {Exploiting Diffusion Prior for Real-World Image Super-Resolution},
  article = {International Journal of Computer Vision},
  year = {2024}
}

License

This project is licensed under NTU S-Lab License 1.0. Redistribution and use should follow this license.

Acknowledgement

This project is based on stablediffusion, latent-diffusion, SPADE, mixture-of-diffusers and BasicSR. Thanks for their awesome work.