# Explainability-in-Action: Enabling Expressive Manipulation and Tacit Understanding by Bending Diffusion Models in ComfyUI

arXiv: https://arxiv.org/abs/2508.07183 · HTML: https://mlsanity.com/paper/2508.07183/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 10 Aug 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 6 of 6)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Active Divergence with Generative Deep Learning -- A Survey and Taxonomy](https://mlsanity.com/paper/2107.05599/) (2021)
- [XAIxArts Manifesto: Explainable AI for the Arts](https://mlsanity.com/paper/2502.21220/) (2025)
- [Towards Directive Explanations: Crafting Explainable AI Systems for Actionable Human-AI Interactions](https://mlsanity.com/paper/2401.04118/) (2023)
- [Explainability Paths for Sustained Artistic Practice with AI](https://mlsanity.com/paper/2407.15216/) (2024)
- [Network Bending of Diffusion Models for Audio-Visual Generation](https://mlsanity.com/paper/2406.19589/) (2024)

## Built on by (most cited first, 1 of 1)

- [GLEaN: A Text-to-image Bias Detection Approach for Public Comprehension](https://mlsanity.com/paper/2604.09923/) (2026)

## Abstract (arXiv)

Explainable AI (XAI) in creative contexts can go beyond transparency to support artistic engagement, modifiability, and sustained practice. While curated datasets and training human-scale models can offer artists greater agency and control, large-scale generative models like text-to-image diffusion systems often obscure these possibilities. We suggest that even large models can be treated as creative materials if their internal structure is exposed and manipulable. We propose a craft-based approach to explainability rooted in long-term, hands-on engagement akin to Sch"on's "reflection-in-action" and demonstrate its application through a model-bending and inspection plugin integrated into the node-based interface of ComfyUI. We demonstrate that by interactively manipulating different parts of a generative model, artists can develop an intuition about how each component influences the output.