-
Nanjing University
- Nanjing, China
-
01:12
(UTC +08:00) - https://zijian-wu.github.io/
Highlights
- Pro
Starred repositories
Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model
WorldPlay: Interactive World Modeling with Real-Time Latency and Geometric Consistency
HunyuanVideo-1.5: A leading lightweight video generation model
[ICLR'25] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
Official Repo for Self-Forcing++ High Quality Long Video Generation
Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"
"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training" official implementation.
Native and Compact Structured Latents for 3D Generation
PersonaLive! : Expressive Portrait Image Animation for Live Streaming
Pose Extraction & Rendering for SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations
[TPAMI 2025] ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
Tiny AutoEncoder for Hunyuan Video (and other video models)
Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"
[ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
MotionStream: Real-Time Video Generation with Interactive Motion Controls
One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer
Offical Implementation of SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations
StreamDiffusion, Live Stream APP
SOTAMak1r / Infinite-Forcing
Forked from guandeh17/Self-ForcingInfinite-Forcing: Towards Infinite-Long Video Generation
Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
📷 Camera-controlled text-to-video generation, now with intrinsics, distortion and orientation control!
[ACM MM 2025] Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis
Implementation for ”Bringing Your Portrait to 3D Presence“
WorldGrow: Generating Infinite 3D World [AAAI 2026 Oral]