Image Generation

Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation

Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

Nested Attention: Semantic-aware Attention Values for Concept Personalization

MLLM-as-a-Judge for Image Safety without Human Labeling

VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control

Edicho: Consistent Image Editing in the Wild

Bringing Objects to Life: 4D generation from 3D objects

VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models

1.58-bit FLUX

Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching

CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up

UIP2P: Unsupervised Instruction-based Image Editing via Cycle Edit Consistency

Parallelized Autoregressive Visual Generation

LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis

Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion

PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and Generation

FashionComposer: Compositional Fashion Image Generation

Autoregressive Video Generation without Vector Quantization

ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers

Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models