PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 15, 2026Electronics0 citationsOpen Access

Knit-Edit: A Unified Multi-Task Editing Framework for Knitted Garments

View Full Paper
ZWZhen WuQFQiang FuJLJing Li

Key Points

  • The aim is to enhance the editing process of knitted garments using a unified editing framework.
  • Developed a framework called Knit-Edit for garment editing.
  • Introduced EditLoRI for task decoupling using Low-Rank Adaptation.
  • Implemented a guidance strategy with Bounding Boxes to improve editing accuracy.
  • Significantly improved controllability compared to existing methods.
  • Addressed issues of texture collapse in editing knitted garments.

Abstract

Generative Artificial Intelligence has shown immense potential in industrial design. However, applying Diffusion Transformers to precision manufacturing faces a critical bottleneck: the trade-off between flexible multi-task editing and high-fidelity texture preservation. Existing methods often suffer from “texture collapse” when merging multiple adapters, failing to maintain the intricate topological structures required for industrial standards. To address this, we present Knit-Edit, a unified framework for high-precision knitted garment editing. Our core contribution is EditLoRI, a novel task decoupling mechanism utilizing orthogonal Low-Rank Adaptation. By projecting task-specific gradients into orthogonal subspaces, EditLoRI enables the interference-free composition of multiple editing capabilities within a single lightweight model. Furthermore, we introduce a structure-preserving spatial guidance strategy using Bounding Boxes to resolve the localization ambiguity of text prompts. Validated on our constructed KnitEdit dataset, the proposed method significantly outperforms state-of-the-art baselines in controllability and structural fidelity, offering a robust solution for intelligent generative manufacturing.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Wu et al. (2026) studied this question.

synapsesocial.com/papers/69b606af83145bc643d1ce60https://doi.org/10.3390/electronics15061208
Ask AI
Helpful
Bookmark
Share
View Full Paper