封面图片

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Guardado en:
发表在:arXiv.org (Dec 5, 2024), p. n/a
主要作者: Bai, Jinbin
其他作者: Tian Ye, Chow, Wei, Song, Enxin, Qing-Guo, Chen, Li, Xiangtai, Dong, Zhen, Zhu, Lei, Shuicheng Yan
出版:
Cornell University Library, arXiv.org
主题:
Diffusion rate
Image compression
Image resolution
Image quality
Image enhancement
Image processing
Synthesis
High resolution
在线阅读:Citation/Abstract
Full text outside of ProQuest
标签: 添加标签
没有标签, 成为第一个标记此记录!
摘要:We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL. By incorporating a comprehensive suite of architectural innovations, advanced positional encoding strategies, and optimized sampling conditions, Meissonic substantially improves MIM's performance and efficiency. Additionally, we leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers to further enhance image fidelity and resolution. Our model not only matches but often exceeds the performance of existing models like SDXL in generating high-quality, high-resolution images. Extensive experiments validate Meissonic's capabilities, demonstrating its potential as a new standard in text-to-image synthesis. We release a model checkpoint capable of producing \(1024 \times 1024\) resolution images.
ISSN:2331-8422
Fuente:Engineering Database