5 papers
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Dong Chen, Fangyun Wei, Ziyu Wan +18
We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with more than 6B parameters acro…
InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
Yang Yue, Fangyun Wei, Tianyu He +10
Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregressive generators built on d…
Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers
Wenhao Sun, Ji Li, Zhaoqiang Liu
Diffusion Transformers have established a new state-of-the-art in image synthesis, but the high computational cost of iterative sampling severely hampers their practical deployment…
MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning
Yuxuan Luo, Yuhui Yuan, Junwen Chen +6
In this paper, we introduce knowledge image generation as a new task, alongside the Massive Multi-Discipline Multi-Tier Knowledge-Image Generation Benchmark (MMMG) to probe the rea…
ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation
Yifan Pu, Yiming Zhao, Zhicong Tang +14
Multi-layer image generation is a fundamental task that enables users to isolate, select, and edit specific image layers, thereby revolutionizing interactions with generative model…