Difan Liu

11

Papers

34

Total Citations

Papers (11)

Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models

Visual Persona: Foundation Model for Full-Body Human Customization

DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization

VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation

Rethinking Layered Graphic Design Generation with a Top-Down Approach

SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model

NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation

Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation

Move-in-2D: 2D-Conditioned Human Motion Generation

VecFusion: Vector Font Generation with Diffusion

VideoGigaGAN: Towards Detail-rich Video Super-Resolution