Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model

About

Unified generation models aim to handle diverse tasks across modalities -- such as text generation, image generation, and vision-language reasoning -- within a single architecture and decoding paradigm. Autoregressive unified models suffer from slow inference due to sequential decoding, and non-autoregressive unified models suffer from weak generalization due to limited pretrained backbones. We introduce Muddit, a unified discrete diffusion transformer that enables fast and parallel generation across both text and image modalities. Unlike prior unified diffusion models trained from scratch, Muddit integrates strong visual priors from a pretrained text-to-image backbone with a lightweight text decoder, enabling flexible and high-quality multimodal generation under a unified architecture. Empirical results show that Muddit achieves competitive or superior performance compared to significantly larger autoregressive models in both quality and efficiency. The work highlights the potential of purely discrete diffusion, when equipped with strong visual priors, as a scalable and effective backbone for unified generation.

Qingyu Shi, Jinbin Bai, Zhuoran Zhao, Wenhao Chai, Kaidong Yu, Jianzong Wu, Shuangyong Song, Yunhai Tong, Xiangtai Li, Xuelong Li, Shuicheng Yan• 2025

Related benchmarks

TaskDatasetResultRank
Text-to-Image GenerationGenEval
Overall Score90
467
Mathematical ReasoningMathVista (testmini)
Accuracy79.1
51
Visual ReasoningMM-Vet
Score76.2
34
Text-to-Image GenerationDPGBench
DPGBench Score86.37
31
Multi-discipline ReasoningMMMU standard (test)
MMMU Score66.6
14
Multimodal UnderstandingMMBench v1.1 (dev)
MMBench Score82.8
14
Visual Text Reasoning and RecognitionOCRBench v2
Recognition Accuracy64.9
14
Multimodal UnderstandingMME standard (test)
MME-P Score1.70e+3
7
Visual PerceptionMMVP standard (test)
MMVP Score74.1
6
Showing 9 of 9 rows

Other info

Follow for update