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

Jinbin Bai, Tian Ye, Wei Chow, Enxin Song, Qing-Guo Chen +4 more
2/12/2026

No official code found. Best implementation: viiika/Meissonic (344 stars, Apache-2.0, last commit 2026-02-04).

Semantic Scholar

Code Implementations(1)

viiika/MeissonicCommunity66%
Apache-2.0

[ICLR 2025] Official Implementation of Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

34412Shell, PythonOct 13, 20248 months agoApache-2.0
image-to-imagenon-autoregressive-transformerstext-to-image

Cite this paper

@article{bai2026meissonic,
  title  = {Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis},
  author = {Jinbin Bai and Tian Ye and Wei Chow and Enxin Song and Qing-Guo Chen and Xiangtai Li and Zhen Dong and Lei Zhu and Shuicheng Yan},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:d5939a4e2488bdb1c7d07a62703dd7f5782ae9ea},
  journal = {ICLR 2025 2025}
}

Discussion