Training-Free Consistency Pipeline for Fashion Repose

TL;DR

FashionRepose is a training-free, zero-shot pipeline that enables precise, real-time non-rigid pose editing of fashion images while preserving identity and branding, addressing key industrial needs.

Contribution

It introduces a novel, training-free method for non-rigid pose editing in fashion images, eliminating the need for custom training data and enabling near real-time performance.

Findings

Effective pose editing of fashion images without training.

Maintains object identity and branding attributes during edits.

Operates in near real-time, suitable for industrial applications.

Abstract

Recent advancements in diffusion models have significantly broadened the possibilities for editing images of real-world objects. However, performing non-rigid transformations, such as changing the pose of objects or image-based conditioning, remains challenging. Maintaining object identity during these edits is difficult, and current methods often fall short of the precision needed for industrial applications, where consistency is critical. Additionally, fine-tuning diffusion models requires custom training data, which is not always accessible in real-world scenarios. This work introduces FashionRepose, a training-free pipeline for non-rigid pose editing specifically designed for the fashion industry. The approach integrates off-the-shelf models to adjust poses of long-sleeve garments, maintaining identity and branding attributes. FashionRepose uses a zero-shot approach to perform these edits in near real-time, eliminating the need for specialized training. consistent image editing. The solution holds potential for applications in the fashion industry and other fields demanding identity preservation in image editing.