Mr Umran Ali U.Ali@salford.ac.uk
Senior Lecturer
FluxZayn: An Extension for Stable Diffusion WebUI Forge 300 word overview
This practice-led, auto-ethnographic case study documents the creation of FluxZayn, a Python-based extension for the Stable Diffusion WebUI Forge platform that enables one-click transparent PNG generation. Motivated by a persistent challenge in my own creative workflow—the laborious process of manually removing backgrounds from 2D game assets—this research explores "vibe coding," an intuitive, artist-centric development method using generative AI assistants like ChatGPT, Claude, and Gemini Pro.
This project is underpinned by the concept of democratizing tool development for creative practitioners and investigates the following questions:
Can a non-programmer successfully "vibe code" a complex, functional software tool?
What are the barriers and opportunities in AI-assisted prototyping for artists and designers?
How does the choice of generative AI assistant (ChatGPT vs. Claude vs. Gemini) impact the development process and outcome?
Can this process empower creators to build the specific tools they need, bridging gaps in existing software ecosystems?
The aim of this study was to move beyond theoretical discussions of AI-assisted coding and test its practical limits by developing a needed tool that was previously beyond my technical capabilities. By meticulously documenting the iterative design, development, and debugging process, this research offers a reflective account of the potential and challenges of this emerging paradigm.
The initial findings reveal that generative AI, particularly Gemini Pro, can indeed act as a powerful collaborator, enabling the creation of sophisticated software without formal programming expertise. This study contributes to the fields of human-AI collaboration, creative practice, and practice-led research by demonstrating how "vibe coding" can lower technical barriers, fostering a new class of artist-developers who can shape their own digital tools. The findings will be further explored through the continued open-source development of FluxZayn and future publications.
Online Publication Date | Aug 5, 2025 |
---|---|
Publication Date | Aug 5, 2025 |
Deposit Date | Aug 5, 2025 |
DOI | https://doi.org/10.17866/rd.salford.29675186.v1 |
Collection Date | Aug 5, 2025 |
FluxZayn: An Extension for Stable Diffusion WebUI Forge
(2025)
Digital Artefact
FluxZayn: Example Outputs
(2025)
Digital Artefact
FluxZayn Video Demonstration
(2025)
Digital Artefact
FluxZayn: Research Timeline
(2025)
Data
FluxZayn: Contents Page
(2025)
Data
About USIR
Administrator e-mail: library-research@salford.ac.uk
This application uses the following open-source libraries:
Apache License Version 2.0 (http://www.apache.org/licenses/)
Apache License Version 2.0 (http://www.apache.org/licenses/)
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2025
Advanced Search