TensorX
返回文献探索

Paper · arXiv 2408.14176

SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher

Trung Dao, Thuan Hoang Nguyen, Thanh Le, Duc Vu, Khoi Nguyen, Cuong Pham, Anh Tran

62 upvotesAugust 26, 2024arXiv 预印本
AI 摘要

Enhancements to SwiftBrush through improved weight initialization, efficient LoRA training, and novel clamped CLIP loss achieve state-of-the-art image quality while maintaining generative diversity.

one-step text-to-image diffusion modelmulti-step Stable Diffusionquality-diversity trade-offweight initializationefficient LoRA trainingclamped CLIP lossimage-text alignmentFID

Abstract

In this paper, we aim to enhance the performance of SwiftBrush, a prominent one-step text-to-image diffusion model, to be competitive with its multi-step Stable Diffusion counterpart. Initially, we explore the quality-diversity trade-off between SwiftBrush and SD Turbo: the former excels in image diversity, while the latter excels in image quality. This observation motivates our proposed modifications in the training methodology, including better weight initialization and efficient LoRA training. Moreover, our introduction of a novel clamped CLIP loss enhances image-text alignment and results in improved image quality. Remarkably, by combining the weights of models trained with efficient LoRA and full training, we achieve a new state-of-the-art one-step diffusion model, achieving an FID of 8.14 and surpassing all GAN-based and multi-step Stable Diffusion models. The evaluation code is available at: https://github.com/vinairesearch/swiftbrushv2.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher | TensorX