Imagen de Portada

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

Guardado en:
Publicado en:arXiv.org (Dec 5, 2024), p. n/a
Autor principal: Bai, Jinbin
Otros Autores: Tian Ye, Chow, Wei, Song, Enxin, Qing-Guo, Chen, Li, Xiangtai, Dong, Zhen, Zhu, Lei, Shuicheng Yan
Publicado:
Cornell University Library, arXiv.org
Materias:
Diffusion rate
Image compression
Image resolution
Image quality
Image enhancement
Image processing
Synthesis
High resolution
Acceso en línea:Citation/Abstract
Full text outside of ProQuest
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen: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