cjwbw/rudalle-sr

Public
Real-ESRGAN super-resolution model from ruDALL-E

Run time and cost

Predictions run on Nvidia T4 GPU hardware. Predictions typically complete within 25 seconds. The predict time for this model varies significantly based on the inputs.

This is the Real-ESRGAN super-resolution model from ruDALL-E.

Real-ESRGAN was created by Xintao Wang, Liangbin Xie, Chao Dong, and Ying Shan. Paper
Re-trained version of Real-ESRGAN was created by Igor Pavlov
ruDALL-E was created by Alex Shonenkov, Tatiana Shavrina, et al., at Sberbank AI

Citation

@InProceedings{wang2021realesrgan,
    author    = {Xintao Wang and Liangbin Xie and Chao Dong and Ying Shan},
    title     = {Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data},
    booktitle = {International Conference on Computer Vision Workshops (ICCVW)},
    date      = {2021}
}