Qian HE

10

Papers

137

Total Citations

Papers (10)

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

RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization

AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion

Mask^2DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation

AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models

HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis

DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations

I2VControl: Disentangled and Unified Video Motion Synthesis Control

Less-to-More Generalization: Unlocking More Controllability by In-Context Generation

OneGT: One-Shot Geometry-Texture Neural Rendering for Head Avatars