VIS'24 · Conference paper
Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion
See how Stable Diffusion turns text into images
Abstract
Diffusion-based generative models' impressive ability to create convincing images has garnered global attention. However, their complex structures and operations often pose challenges for non-experts to grasp. We present Diffusion Explainer, the first interactive visualization tool that explains how Stable Diffusion transforms text prompts into images. Diffusion Explainer tightly integrates a visual overview of Stable Diffusion's complex structure with explanations of the underlying operations. By comparing image generation of prompt variants, users can discover the impact of keyword changes on image generation. A 56-participant user study demonstrates that Diffusion Explainer offers substantial learning benefits to non-experts. Our tool has been used by over 10,300 users from 124 countries at https://poloclub.github.io/diffusion-explainer/.
In the press
- Quanta MagazineHow Physics Made Modern AI Possible
Cite
@article{lee2023diffusion,
title={Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion},
author={Lee, Seongmin and Hoover, Benjamin and Strobelt, Hendrik and Wang, Zijie J and Peng, ShengYun and Wright, Austin and Li, Kevin and Park, Haekyu and Yang, Haoyang and Chau, Duen Horng},
journal={arXiv preprint arXiv:2305.03509},
year={2023}
}
Seongmin Lee
Benjamin Hoover
Hendrik Strobelt
Zijie J. Wang
ShengYun Peng
Austin Wright
Kevin Li
Haekyu Park
Haoyang Yang
Polo Chau