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

2024/10/10 by Jinbin Bai, Ye Tian, Tian Ye +14 · 2 voices · 20 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Generative Adversarial Networks and Image Synthesis #Image Retrieval and Classification Techniques #cs.CV

paper · pdf · doi:10.48550/arxiv.2410.08261

openalex publication_date 2024/10/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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 × 1024 resolution images.

Cited by

• dRAE: Representation Autoencoder with Hyper-Spherical Codes
• Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation
• Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis
• A Survey on Diffusion Language Models
• PairFlow: Closed-Form Source-Target Coupling for Few-Step Generation in Discrete Flow Models
• RecTok: Reconstruction Distillation along Rectified Flow
• EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing
• Accelerating Inference of Masked Image Generators via Reinforcement Learning
• MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation
• Uniform Discrete Diffusion with Metric Path for Video Generation
• From Masks to Worlds: A Hitchhiker's Guide to World Models
• Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation
• Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
• Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
• Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding
• TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion
• Token Painter: Training-Free Text-Guided Image Inpainting via Mask Autoregressive Models
• MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control
• UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation
• Personalized Safety Alignment for Text-to-Image Diffusion Models

Discussions

• Meissonic, High-Resolution Text-to-Image Synthesis on consumer graphics cards [hn, 65 points, 4 comments]
• Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis [lemmy, 3 points, 0 comments]

Related

• Muse: Text-To-Image Generation via Masked Generative Transformers
• Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer
• RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model
• SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
• Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis