Saved in:
Bibliographic Details
Main Authors: Abuzuraiq, Ahmed M., Pasquier, Philippe
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.07183
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912530780127232
author Abuzuraiq, Ahmed M.
Pasquier, Philippe
author_facet Abuzuraiq, Ahmed M.
Pasquier, Philippe
contents 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 Schön'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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07183
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Explainability-in-Action: Enabling Expressive Manipulation and Tacit Understanding by Bending Diffusion Models in ComfyUI
Abuzuraiq, Ahmed M.
Pasquier, Philippe
Human-Computer Interaction
Artificial Intelligence
Machine Learning
Multimedia
I.2; J.5
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 Schön'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.
title Explainability-in-Action: Enabling Expressive Manipulation and Tacit Understanding by Bending Diffusion Models in ComfyUI
topic Human-Computer Interaction
Artificial Intelligence
Machine Learning
Multimedia
I.2; J.5
url https://arxiv.org/abs/2508.07183