nightmareai / latent-sr

Upscale images with the latent diffusion superresolution model

  • Public
  • 114.4K runs
  • GitHub
  • License

Run time and cost

This model costs approximately $0.023 to run on Replicate, or 43 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 T4 GPU hardware. Predictions typically complete within 102 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This is an implementation of the latent diffusion superresolution upscaler found in this notebook:

https://colab.research.google.com/drive/1xqzUi2iXQXDqXBHQGP9Mqt2YrYW6cx-J?usp=sharing#scrollTo=aCoHC2jbq_Ka

Results from testing so far show it to be very good with textures and fine details on generated images, but poor on real-world jobs.

@misc{rombach2021highresolution,
      title={High-Resolution Image Synthesis with Latent Diffusion Models}, 
      author={Robin Rombach and Andreas Blattmann and Dominik Lorenz and Patrick Esser and Björn Ommer},
      year={2021},
      eprint={2112.10752},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}