Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

Official implementation of the paper "GUAVA: Generalizable Upper Body 3D Gaussian Avatar" [ICCV 2025]

HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

Light Video Generation Inference Framework

🚀 [ICLR 2025] Pytorch implementation of 'Fast Feedforward 3D Gaussian Splatting Compression'

News: the 10k dataset is ready for download.

Try-On Master-1: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-wise Diffusion Transformer Framework

[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation

EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

Wan: Open and Advanced Large-Scale Video Generative Models

(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

[ICCV2025] LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds

The official implementation of ICCV'25 paper "FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution"

[NeurIPS 2025] The official code for "IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation"

Phantom-Data: Towards a General Subject-Consistent Video Generation Dataset

[SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

[CSUR] A Survey on Video Diffusion Models

Official project page of MTVCrafter, a new paradigm for animating arbitrary characters with 4D motion tokens.

📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives

MagicTryOn is a video virtual try-on framework based on a large-scale video diffusion Transformer.

AniCrafter: Customizing Realistic Human-Centric Animation via Avatar-Background Conditioning in Video Diffusion Models

Code for "Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates", SIGGRAPH2025

[CVPR 2025] Official implementation of "AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models"