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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yeh, Shih-Ying, Hsieh, Yu-Guan, Gao, Zhidong, Yang, Bernard B W, Oh, Giyeong, Gong, Yanmin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914708598030336
author Yeh, Shih-Ying
Hsieh, Yu-Guan
Gao, Zhidong
Yang, Bernard B W
Oh, Giyeong
Gong, Yanmin
author_facet Yeh, Shih-Ying
Hsieh, Yu-Guan
Gao, Zhidong
Yang, Bernard B W
Oh, Giyeong
Gong, Yanmin
contents 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) [https://github.com/KohakuBlueleaf/LyCORIS], 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.
format Preprint
id arxiv_https___arxiv_org_abs_2309_14859
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation
Yeh, Shih-Ying
Hsieh, Yu-Guan
Gao, Zhidong
Yang, Bernard B W
Oh, Giyeong
Gong, Yanmin
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Machine Learning
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) [https://github.com/KohakuBlueleaf/LyCORIS], 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.
title Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Machine Learning
url https://arxiv.org/abs/2309.14859