Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
Sábháilte in:
| Foilsithe in: | arXiv.org (Dec 5, 2024), p. n/a |
|---|---|
| Príomhchruthaitheoir: | |
| Rannpháirtithe: | , , , , , , , |
| Foilsithe / Cruthaithe: |
Cornell University Library, arXiv.org
|
| Ábhair: | |
| Rochtain ar líne: | Citation/Abstract Full text outside of ProQuest |
| Clibeanna: |
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 |