zsxkib / aura-sr-v2

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

  • Public
  • 1.8K runs
  • GitHub
  • Paper
  • License
Run with an API
Playground API Examples README Versions

Examples

View more

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 A40 GPU hardware. Predictions typically complete within 3 minutes. The predict time for this model varies significantly based on the inputs.

Readme

✨ 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!