BIG.art: Using Machine Learning to Create High-Res Fine Art

How to use GLIDE and BSRGAN to create ultra-high-resolution paintings with fine details

By Robert. A Gonsalves

You can see my article on Medium.

The source code and generated images are released under the CC BY-SA license.

Google Colab

• BIG.art Image Creation

Acknowledgements

• A. Nichol et al., GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models (2022)
• K. Zhang et al., BSRGAN: Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (2021)
• P. Dhariwal and A. Nichol, Diffusion Models Beat GANs on Image Synthesis (2021)
• J. Ho and C. Saharia, High Fidelity Image Generation Using Diffusion Models (2021)
• P. Esser, R. Rombach, and B. Ommer, VQGAN: Taming Transformers for High-Resolution Image Synthesis (2020)

Citation

To cite this repository:

@software{BIG.art,
  author  = {Gonsalves, Robert A.},
  title   = {BIG.art: Using Machine Learning to Create High-Res Fine Art},
  url     = {https://github.com/robgon-art/BIG.art},
  year    = 2022,
  month   = April
}