12 papers
MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale
Zhicong Tang, Zhao Zhang, Jingye Chen +6
Layered image generation and editing is a fundamental capability that enables layer-wise reuse, editing, and composition of generated visual content, analogous to word-level editin…
Pareto-Guided Optimal Transport for Multi-Reward Alignment
Ying Ba, Tianyu Zhang, Mohan Zhou +5
Text-to-image generation models have achieved remarkable progress in preference optimization, yet achieving robust alignment across diverse reward models remains a significant chal…
Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation
Zihao Wang, Yuxiang Wei, Xinpeng Zhou +5
Text-to-image generation has advanced rapidly, yet it still struggles to capture the nuanced user preferences. Existing approaches typically rely on multimodal large language model…
PrefGen: Multimodal Preference Learning for Preference-Conditioned Image Generation
Wenyi Mo, Tianyu Zhang, Yalong Bai +3
Preference-conditioned image generation seeks to adapt generative models to individual users, producing outputs that reflect personal aesthetic choices beyond the given textual pro…
PreferThinker: Reasoning-based Personalized Image Preference Assessment
Shengqi Xu, Xinpeng Zhou, Yabo Zhang +6
Personalized image preference assessment aims to evaluate an individual user's image preferences by relying only on a small set of reference images as prior information. Existing m…
Learning User Preferences for Image Generation Model
Wenyi Mo, Ying Ba, Tianyu Zhang +2
User preference prediction requires a comprehensive and accurate understanding of individual tastes. This includes both surface-level attributes, such as color and style, and deepe…
Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment
Ying Ba, Tianyu Zhang, Yalong Bai +4
Contemporary image generation systems have achieved high fidelity and superior aesthetic quality beyond basic text-image alignment. However, existing evaluation frameworks have fai…
V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation
Guiwei Zhang, Tianyu Zhang, Mohan Zhou +2
We propose V2Flow, a novel tokenizer that produces discrete visual tokens capable of high-fidelity reconstruction, while ensuring structural and latent distribution alignment with…
Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing
Wenyi Mo, Tianyu Zhang, Yalong Bai +2
Text-guided image generation and editing using diffusion models have achieved remarkable advancements. Among these, tuning-free methods have gained attention for their ability to p…
STAR: Scale-wise Text-conditioned AutoRegressive image generation
Xiaoxiao Ma, Mohan Zhou, Tao Liang +5
We introduce STAR, a text-to-image model that employs a scale-wise auto-regressive paradigm. Unlike VAR, which is constrained to class-conditioned synthesis for images up to 256$\t…
Dynamic Prompt Optimizing for Text-to-Image Generation
Wenyi Mo, Tianyu Zhang, Yalong Bai +3
Text-to-image generative models, specifically those based on diffusion models like Imagen and Stable Diffusion, have made substantial advancements. Recently, there has been a surge…
StyleInject: Parameter Efficient Tuning of Text-to-Image Diffusion Models
Mohan Zhou, Yalong Bai, Qing Yang +1
The ability to fine-tune generative models for text-to-image generation tasks is crucial, particularly facing the complexity involved in accurately interpreting and visualizing tex…