zsxkib / aura-sr-v2

AuraSR v2: Second-gen GAN-based Super-Resolution for real-world applications

  • Public
  • 1.4K runs
  • GitHub
  • Paper
  • License
Run with an API
Playground API Examples README Versions

✨ AuraSR v2: Advanced GAN Super-Resolution for Images 🖼️

Replicate

AuraSR v2 is an improved GAN-based super-resolution tool that enhances image clarity and size. Based on the GigaGAN concept and optimized for real-world applications, it excels with a wide range of image types.

See AuraSR v2 in action

🎨 Features

  • Upscales PNG, WebP, JPEG, and other common image formats
  • Supports 4x upscaling with improved quality
  • Efficient processing with overlapped tile technique
  • Optimized for both AI-generated and high-quality photographs

⚠️ Important Notes

AuraSR v2 is more versatile than its predecessor but still has some considerations:

  1. Excellent results with a wide range of image types, including compressed formats
  2. Improved handling of compression artifacts
  3. Enhanced performance on real-world photographs
  4. Ideal for upscaling both AI-generated and high-quality natural images

🛠️ Usage

Input Parameters

  • image: The input image to upscale (supports various formats including PNG, WebP, JPEG)
  • scale_factor: Fixed at 4x upscaling

Example

import replicate
output = replicate.run(
    "zsxkib/aura-sr-v2:<VERSION>",
    input={
        "image": open("path/to/your/image.jpg", "rb"),
    }
)
print(output)

🙌 Acknowledgements

  • fal.ai for the original AuraSR implementation and v2 improvements
  • lucidrains for the unofficial PyTorch implementation of GigaGAN

Citation

If you use this model in your research or applications, please cite the original GigaGAN paper:

@article{DBLP:journals/corr/abs-2303-05511,
  author    = {Minguk Kang and
               Jaesik Park and
               Namhyuk Ahn and
               Sungsoo Ahn and
               Kibeom Hong and
               Bohyung Han},
  title     = {GigaGAN: Large-scale GAN for Text-to-Image Synthesis},
  journal   = {CoRR},
  volume    = {abs/2303.05511},
  year      = {2023},
  url       = {https://arxiv.org/abs/2303.05511},
  eprinttype = {arXiv},
  eprint    = {2303.05511},
  timestamp = {Tue, 14 Mar 2023 17:06:10 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2303-05511.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

License

This model is released under the Apache 2.0 license.

🐦 Connect

Questions or feedback? Follow me on Twitter @zsakib_ and let’s chat!