Recursive InPainting with Stable Difussion 2 Inpainting

  1. Javier, Conde 1
  2. Miguel, González 1
  3. Gonzalo, Martínez 2
  4. Fernando, Moral 3
  5. Elena, Merino-Gómez 4
  6. Pedro, Reviriego 1
  1. 1 Universidad Politécnica de Madrid
    info

    Universidad Politécnica de Madrid

    Madrid, España

    ROR https://ror.org/03n6nwv02

  2. 2 Universidad Carlos III de Madrid
    info

    Universidad Carlos III de Madrid

    Madrid, España

    ROR https://ror.org/03ths8210

  3. 3 Universidad Antonio Nebrija
  4. 4 Universidad de Valladolid
    info

    Universidad de Valladolid

    Valladolid, España

    ROR https://ror.org/01fvbaw18

Editor: Zenodo

Año de publicación: 2024

Tipo: Dataset

Resumen

Recursive inpainting with Stable Difussion The dataset contains images extracted from WikiArt that have been recursively versioned using inpainting techniques with a version of the Stable Diffusion model oriented towards instructional inpainting called stable-diffusion-2-inpainting.   The dataset contains two folders with two different experiments. Each experiment consists of performing recursive inpainting on 512x512 px images until reaching a percentage of pixels affected by the inpainting of 400% compared to the original image. Each experiment contains the following files: original_imgs_grid.png file with all the base images in an ordered grid. mask_64x64/[number_figure]_64x64.png with the inpainting version of [number_figure] and 64x64 mask mask_128x128/[number_figure]_128x128.png with the inpainting version of [number_figure] and 128x128 mask mask_256x256/[number_figure]_256x256.png with the inpainting version of [number_figure] and 256x256 mask lpips_distances.xlsx with the results of applying the Learned Perceptual Image Path Similarity (LPIPS) metric in its variants SqueezeNet, AlexNet, and VGG. The metrics are calculated with respect to the original image and the previous image. There are two different experiments: lpips_distances_100_images_1_seed: contains recursive inpaintings of 100 different images with a single seed. This allows the analysis of different images when performing recursive inpainting. lpips_distances_10_images_15_seeds: contains recursive inpaintings of 10 different images with 15 different seeds. This allows the analysis of the differences in inpaintings when applying different seeds in the inpainting on the same image. The folder code includes the a README.md with the instructions and the scripts to run the experiments