What question did this study set out to answer?

This research aims to improve the integration of AI in fashion design through a controllable diffusion framework for prototyping.

June 19, 2026

Controllable Generative Systems for Fashion Prototyping: A Human– AI Collaborative Framework Based on Diffusion Models

Key Points

This research aims to improve the integration of AI in fashion design through a controllable diffusion framework for prototyping.
Developed a human-in-the-loop diffusion framework for virtual fashion prototyping.
Conducted user studies with professional fashion designers to compare the framework against GAN and diffusion baselines.
Evaluated metrics including FID, LPIPS, SSIM, and Human Score on the DeepFashion2 dataset.
The framework outperformed all baseline models across FID, LPIPS, SSIM, and Human Score metrics.
User studies indicated higher perceived control and lower workload compared to traditional approaches.
Designers found the framework to enhance usability and interaction during the design process.

Abstract

ABSTRACT Generative artificial intelligence is increasingly used in creative industries, yet its application in fashion design often remains limited to visual generation rather than structured design support. This study proposes a human‐in‐the‐loop controllable diffusion framework for virtual fashion prototyping. The pipeline integrates user‐refined garment masks, pose‐guided structural conditioning, sketch‐to‐render edge constraints, and lightweight LoRA style adaptation, enabling localized editing while preserving global body–garment coherence. Unlike prompt‐only image generation, conventional virtual try‐on systems, or downstream 3D production tools, the framework functions as a pre‐production visual ideation layer for designer‐led iterative editing. The study evaluates the framework through quantitative comparison with directly comparable GAN‐ and diffusion‐based baselines on DeepFashion2, using FID, LPIPS, SSIM, and Human Score; ablation analysis of individual control components; and a within‐subject user study design involving professional fashion designers across representative design tasks. A pilot evaluation with six experienced designers is also reported. Results show that the proposed framework outperforms directly comparable baselines across all reported metrics. Pilot findings further indicate higher perceived control, lower workload, and stronger usability than prompt‐only and inpainting baselines. The findings suggest that controllable diffusion can support professional fashion ideation as an interactive prototyping system rather than merely an automated image generator.

AI से पूछें

Bookmark