Use Datasette to explore LAION improved_aesthetics_6plus training data used by Stable DIffusion
For background on this project, see Exploring 12 Million of the 2.3 Billion Images Used to Train Stable Diffusion’s Image Generator.
This tool is no longer available.
Get hundred of million of image+url from the crawling at home dataset and preprocess them
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M u...
Turn any URLs ending in .jpg/.png/.gif into img tags with width 200
Diffusion base mining
High-Resolution Image Synthesis with Latent Diffusion Models
Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.
[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Mode...
Stable Diffusion web UI
[CVPR2024, Highlight] Official code for DragDiffusion
StableSR for Stable Diffusion WebUI - Ultra High-quality Image Upscaler
Datasette plugin that renders binary blob images using data-uris
[IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution
Versatile Diffusion: Text, Images and Variations All in One Diffusion Model, arXiv 2022 / ICCV 2023
A large-scale text-to-image prompt gallery dataset based on Stable Diffusion
Stable Diffusion