lucataco / pasd-magnify

(Academic and Non-commercial use only) Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization

  • Public
  • 39.8K runs
  • L40S
  • GitHub
  • Paper

Input

image
*file

Input image

string
Shift + Return to add a new line

Prompt

Default: "Frog, clean, high-resolution, 8k, best quality, masterpiece"

string
Shift + Return to add a new line

Negative Prompt

Default: "dotted, noise, blur, lowres, oversmooth, longbody, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality"

integer
(minimum: 10, maximum: 50)

Denoise Steps

Default: 20

integer
(minimum: 1, maximum: 4)

Upsample Scale

Default: 2

number
(minimum: 0.5, maximum: 1.5)

Conditioning Scale

Default: 1.1

number
(minimum: 0.5, maximum: 10)

Guidance Scale

Default: 7.5

integer

Random seed. Leave blank to randomize the seed

Output

We were unable to load these images. Please make sure the URLs are valid.

{
  "input": "https://replicate.delivery/pbxt/KBuUhAMqvkXfjTqqOyg1TqIXSzgUhCbjIzaFoNb7fUdkK685/frog.png",
  "outut": "https://replicate.delivery/pbxt/MGJy2aTpJB7dI1sQ49nfZpdQh2pesLIF6cC22ySbGo0LhcKSA/output-20240108153527.jpg"
}
Generated in

Run time and cost

This model costs approximately $0.0097 to run on Replicate, or 103 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 L40S GPU hardware. Predictions typically complete within 10 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Cog implementation of yangxy/PASD

Pixel-Aware Stable Diffusion for Realistic Image Super-Resolution and Personalized Stylization

Realistic Image SR

frog house

Old photo restoration

old old2

License

© Alibaba, 2023. For academic and non-commercial use only.

@inproceedings{yang2023pasd,
    title={Pixel-Aware Stable Diffusion for Realistic Image Super-Resolution and Personalized Stylization},
    author={Tao Yang, Peiran Ren, Xuansong Xie, and Lei Zhang},
    booktitle={Arxiv},
    year={2023}
}