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

Sábháilte in:
Sonraí bibleagrafaíochta
Foilsithe in:arXiv.org (Dec 5, 2024), p. n/a
Príomhchruthaitheoir: Bai, Jinbin
Rannpháirtithe: Tian Ye, Chow, Wei, Song, Enxin, Qing-Guo, Chen, Li, Xiangtai, Dong, Zhen, Zhu, Lei, Shuicheng Yan
Foilsithe / Cruthaithe:
Cornell University Library, arXiv.org
Ábhair:
Rochtain ar líne:Citation/Abstract
Full text outside of ProQuest
Clibeanna: Cuir clib leis
Níl clibeanna ann, Bí ar an gcéad duine le clib a chur leis an taifead seo!

MARC

LEADER 00000nab a2200000uu 4500
001 3116446013
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3116446013 
045 0 |b d20241205 
100 1 |a Bai, Jinbin 
245 1 |a Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis 
260 |b Cornell University Library, arXiv.org  |c Dec 5, 2024 
513 |a Working Paper 
520 3 |a 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. 
653 |a Diffusion rate 
653 |a Image compression 
653 |a Image resolution 
653 |a Image quality 
653 |a Image enhancement 
653 |a Image processing 
653 |a Synthesis 
653 |a High resolution 
700 1 |a Tian Ye 
700 1 |a Chow, Wei 
700 1 |a Song, Enxin 
700 1 |a Qing-Guo, Chen 
700 1 |a Li, Xiangtai 
700 1 |a Dong, Zhen 
700 1 |a Zhu, Lei 
700 1 |a Shuicheng Yan 
773 0 |t arXiv.org  |g (Dec 5, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3116446013/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2410.08261