Picture for Guansong Lu

Guansong Lu

ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance

Add code
Dec 09, 2024
Viaarxiv icon

LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model

Add code
Mar 18, 2024
Viaarxiv icon

PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with Time-Decoupled Training and Reusable Coop-Diffusion

Add code
Dec 29, 2023
Viaarxiv icon

Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images

Add code
Aug 31, 2023
Figure 1 for Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images
Figure 2 for Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images
Figure 3 for Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images
Figure 4 for Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images
Viaarxiv icon

DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment

Add code
Aug 22, 2023
Viaarxiv icon

DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability

Add code
Aug 18, 2023
Viaarxiv icon

Boosting Text-to-Image Diffusion Models with Fine-Grained Semantic Rewards

Add code
Jun 01, 2023
Viaarxiv icon

Entity-Level Text-Guided Image Manipulation

Add code
Feb 22, 2023
Viaarxiv icon

ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation

Add code
Apr 09, 2022
Figure 1 for ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation
Figure 2 for ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation
Figure 3 for ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation
Figure 4 for ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation
Viaarxiv icon

Wukong: 100 Million Large-scale Chinese Cross-modal Pre-training Dataset and A Foundation Framework

Add code
Mar 10, 2022
Figure 1 for Wukong: 100 Million Large-scale Chinese Cross-modal Pre-training Dataset and A Foundation Framework
Figure 2 for Wukong: 100 Million Large-scale Chinese Cross-modal Pre-training Dataset and A Foundation Framework
Figure 3 for Wukong: 100 Million Large-scale Chinese Cross-modal Pre-training Dataset and A Foundation Framework
Figure 4 for Wukong: 100 Million Large-scale Chinese Cross-modal Pre-training Dataset and A Foundation Framework
Viaarxiv icon