Qi Dai

13

Papers

238

Total Citations

Papers (13)

SimDA: Simple Diffusion Adapter for Efficient Video Generation

StableAnimator: High-Quality Identity-Preserving Human Image Animation

AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction

MotionFollower: Editing Video Motion via Score-Guided Diffusion

MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance

REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents

JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers

FaceA-Net: Facial Attribute-Driven ID Preserving Image Generation Network

MotionEditor: Editing Video Motion via Content-Aware Diffusion

HomoGen: Enhanced Video Inpainting via Homography Propagation and Diffusion

MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation

BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition

FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis