paper-with-me

Papers

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

2024-10-10 · Jinbin Bai, Tian Ye, Wei Chow, Enxin Song, Qing-Guo Chen, Xiangtai Li, Zhen Dong, Lei Zhu, Shuicheng Yan

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.

📄 PDF Abstract BibTeX arXiv:2410.08261

Code (1)

viiika/Meissonic 공식 구현 pytorch

Tasks

Feature CompressionImage Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer

2024-11-16 · Shitong Shao, Zikai Zhou, Tian Ye, Lichen Bai 외

Text-to-image diffusion models (DMs) develop at an unprecedented pace, supported by thorough theoretical exploration and empirical analysis. Unfortunately, the discrepancy between DMs and autoregressive models (ARMs) com…

Text Generation

Fast Training of Diffusion Models with Masked Transformers

2023-06-15 · Hongkai Zheng, Weili Nie, Arash Vahdat, Anima Anandkumar

We propose an efficient approach to train large diffusion models with masked transformers. While masked transformers have been extensively explored for representation learning, their application to generative learning is…

DecoderDenoisingRepresentation Learning

UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

2025-08-07 · Wonjun Kang, Byeongkeun Ahn, Minjae Lee, Kevin Galim 외 arxiv

Text-to-image (T2I) generation has been actively studied using Diffusion Models and Autoregressive Models. Recently, Masked Generative Transformers have gained attention as an alternative to Autoregressive Models to over…

Text-to-Image Generation

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers

2023-12-19 · CVPR 2024 1 · Haoyu Ma, Shahin Mahdizadehaghdam, Bichen Wu, Zhipeng Fan 외

Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish t…

Video Editing

Masked Mixers for Language Generation and Retrieval

2024-09-02 · Benjamin L. Badger

Attention mechanisms that confer selective focus on a strict subset of input elements are nearly ubiquitous in language models today. We posit there to be downside to the use of attention: most information present in the…

Causal Language ModelingRetrievalText Generation