Run it on Replicate:

This repo is based on Stable Diffusion by CompVis group: and Stable Inpainting by Runway

The idea is based on this tweet by Matt Henderson

Given a prompt I run txt2img,py with stable-diffusion-v1-5 Then I paste a downscaled version of the image into it's center and inpaint around the center using inpaint.py using this sd-v1-5-inpainting.ckpt from I repeat the inpainting step twice.

Then zoom in by upscaling the image and cuting it to the original size while pasting the "center" image in its due area.

hf_hub_download(repo_id="runwayml/stable-diffusion-v1-5", filename="v1-5-pruned-emaonly.ckpt", cache_dir=".", use_auth_token=) hf_hub_download(repo_id="runwayml/stable-diffusion-inpainting", filename="sd-v1-5-inpainting.ckpt", cache_dir=".", use_auth_token=)

python3 scripts/inf_zoom.py <your prompt>

@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}
}