12 papers
RecTok: Reconstruction Distillation along Rectified Flow
Qingyu Shi, Size Wu, Jinbin Bai +5
Visual tokenizers play a crucial role in diffusion models. The dimensionality of latent space governs both reconstruction fidelity and the semantic expressiveness of the latent fea…
EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing
Wei Chow, Linfeng Li, Lingdong Kong +13
Recent advances in diffusion models (DMs) have achieved exceptional visual quality in image editing tasks. However, the global denoising dynamics of DMs inherently conflate local e…
Personalized Safety Alignment for Text-to-Image Diffusion Models
Yu Lei, Jinbin Bai, Qingyu Shi +4
Text-to-image diffusion models have revolutionized visual content generation, yet their deployment is hindered by a fundamental limitation: safety mechanisms enforce rigid, uniform…
JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent
Yunlong Lin, Zixu Lin, Kunjie Lin +8
Photo retouching has become integral to contemporary visual storytelling, enabling users to capture aesthetics and express creativity. While professional tools such as Adobe Lightr…
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
Qingyu Shi, Jinbin Bai, Zhuoran Zhao +7
Unified generation models aim to handle diverse tasks across modalities -- such as text generation, image generation, and vision-language reasoning -- within a single architecture…
Conditional Panoramic Image Generation via Masked Autoregressive Modeling
Chaoyang Wang, Xiangtai Li, Lu Qi +4
Recent progress in panoramic image generation has underscored two critical limitations in existing approaches. First, most methods are built upon diffusion models, which are inhere…
An Empirical Study of GPT-4o Image Generation Capabilities
Sixiang Chen, Jinbin Bai, Zhuoran Zhao +16
The landscape of image generation has rapidly evolved, from early GAN-based approaches to diffusion models and, most recently, to unified generative architectures that seek to brid…
Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer
Qingyu Shi, Jianzong Wu, Jinbin Bai +4
The motion transfer task aims to transfer motion from a source video to newly generated videos, requiring the model to decouple motion from appearance. Previous diffusion-based met…
Evaluating Image Caption via Cycle-consistent Text-to-Image Generation
Tianyu Cui, Jinbin Bai, Guo-Hua Wang +5
Evaluating image captions typically relies on reference captions, which are costly to obtain and exhibit significant diversity and subjectivity. While reference-free evaluation met…
HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editing
Jinbin Bai, Wei Chow, Ling Yang +4
We present HumanEdit, a high-quality, human-rewarded dataset specifically designed for instruction-guided image editing, enabling precise and diverse image manipulations through op…
DreamRelation: Bridging Customization and Relation Generation
Qingyu Shi, Lu Qi, Jianzong Wu +4
Customized image generation is essential for creating personalized content based on user prompts, allowing large-scale text-to-image diffusion models to more effectively meet indiv…
MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models
Donghao Zhou, Jiancheng Huang, Jinbin Bai +5
Text-to-image diffusion models can generate high-quality images but lack fine-grained control of visual concepts, limiting their creativity. Thus, we introduce component-controllab…