Score: 1

Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models

Published: May 29, 2025 | arXiv ID: 2506.04244v1

By: Farzad Farhadzadeh , Debasmit Das , Shubhankar Borse and more

BigTech Affiliations: Qualcomm

Potential Business Impact:

Lets AI art tools learn new styles instantly.

Business Areas:
Translation Service Professional Services

We introduce ProLoRA, enabling zero-shot adaptation of parameter-efficient fine-tuning in text-to-image diffusion models. ProLoRA transfers pre-trained low-rank adjustments (e.g., LoRA) from a source to a target model without additional training data. This overcomes the limitations of traditional methods that require retraining when switching base models, often challenging due to data constraints. ProLoRA achieves this via projection of source adjustments into the target model's weight space, leveraging subspace and null space similarities and selectively targeting aligned layers. Evaluations on established text-to-image models demonstrate successful knowledge transfer and comparable performance without retraining.

Country of Origin
🇺🇸 United States

Page Count
17 pages

Category
Computer Science:
Artificial Intelligence