Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion

Seongmin Lee, Benjamin Hoover, Hendrik Strobelt, Zijie J. Wang, ShengYun Peng +5 more
5/4/2023
cs.CLcs.AIcs.HC

No official code found. Best implementation: poloclub/diffusion-explainer (486 stars, MIT, last commit 2024-08-31).

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/.

View on arXivView PDF

Code Implementations(1)

poloclub/diffusion-explainerCommunity100%
MIT

Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion

48663CSS, HTMLDec 27, 20222 years agoMIT
clipdeep-learninggenerative-modelinteractive-visualizationmachine-learning+4 more

Similar Papers

Explaining generative diffusion models via visual analysis for interpretable decision-making process

87% match1 repo132024

Emergence and Evolution of Interpretable Concepts in Diffusion Models

86% match1 repo122025

Interactive Visual Learning for Stable Diffusion

86% match2024

Diffusion Explorer: Interactive Exploration of Diffusion Models

85% match2025

DiffusionPID: Interpreting Diffusion via Partial Information Decomposition

85% match2024

Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines

84% match2024

Cite this paper

@article{lee2023diffusion,
  title  = {Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion},
  author = {Seongmin Lee and Benjamin Hoover and Hendrik Strobelt and Zijie J. Wang and ShengYun Peng and Austin Wright and Kevin Li and Haekyu Park and Haoyang Yang and Duen Horng Chau},
  year   = {2023},
  eprint = {2305.03509},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.03509v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.03509.svg)](https://codeofpaper.com/paper/2305.03509)

Discussion