Xinglong Wu

9

Papers

136

Total Citations

Papers (9)

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation

Graphic Design with Large Multimodal Model

DreamOmni: Unified Image Generation and Editing

DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model

DiffIR: Efficient Diffusion Model for Image Restoration

Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring

Clover: Towards a Unified Video-Language Alignment and Fusion Model

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation