Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation

Published: 16 Jan 2024, Last Modified: 09 Mar 2024ICLR 2024 posterEveryoneRevisionsBibTeX
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Text-to-Image, Model Customization, Parameter-Efficient Fine-Tuning, Model Evaluation
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We introduce LyCORIS, an open-source library for parameter-efficient Stable Diffusion fine-tuning, propose a comprehensive evaluation framework, and perform extensive experiments to compare different methods.
Abstract: Text-to-image generative models have garnered immense attention for their ability to produce high-fidelity images from text prompts. Among these, Stable Diffusion distinguishes itself as a leading open-source model in this fast-growing field. However, the intricacies of fine-tuning these models pose multiple challenges from new methodology integration to systematic evaluation. Addressing these issues, this paper introduces LyCORIS (Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion), an open-source library that offers a wide selection of fine-tuning methodologies for Stable Diffusion. Furthermore, we present a thorough framework for the systematic assessment of varied fine-tuning techniques. This framework employs a diverse suite of metrics and delves into multiple facets of fine-tuning, including hyperparameter adjustments and the evaluation with different prompt types across various concept categories. Through this comprehensive approach, our work provides essential insights into the nuanced effects of fine-tuning parameters, bridging the gap between state-of-the-art research and practical application.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
Supplementary Material: pdf
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: generative models
Submission Number: 1940
Loading