Fa-Ting Hong

5

Papers

24

Total Citations

Papers (5)

FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model

Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation

AnyTalk: Multi-modal Driven Multi-domain Talking Head Generation

Free-viewpoint Human Animation with Pose-correlated Reference Selection

Hunyuan-Portrait: Implicit Condition Control for Enhanced Portrait Animation