{"ID":2884048,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.07183","arxiv_id":"2508.07183","title":"Explainability-in-Action: Enabling Expressive Manipulation and Tacit Understanding by Bending Diffusion Models in ComfyUI","abstract":"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.","short_abstract":"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 obscur...","url_abs":"https://arxiv.org/abs/2508.07183","url_pdf":"https://arxiv.org/pdf/2508.07183v1","authors":"[\"Ahmed M. Abuzuraiq\",\"Philippe Pasquier\"]","published":"2025-08-10T05:19:30Z","proceeding":"cs.HC","tasks":"[\"cs.HC\",\"cs.AI\",\"cs.LG\",\"cs.MM\"]","methods":"[\"Diffusion Model\"]","has_code":false}