DNO: Optimizing Diffusion Noise Can Serve As Universal Motion Priors

Official Implementation of the Paper: Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generation (ACMMM 2024)

Official implementation for "Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches" (CVPR 2024)

A generative world for general-purpose robotics & embodied AI learning.

[ARXIV'24] 3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation

Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

XQ-GAN🚀: An Open-source Image Tokenization Framework for Autoregressive Generation

Paper: "From Text to Pose to Image: Improving Diffusion Model Control and Quality"

EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"

[Arxiv 2024] MotionCLR: Motion Generation and Training-free Editing via Understanding Attention Mechanisms

A vector-quantized periodic autoencoder (VQ-PAE) for motion alignment across different morphologies with no supervision [SIGGRAPH 2024]

A suite of image and video neural tokenizers

Janus-Series: Unified Multimodal Understanding and Generation Models

MikuDance: Animating Character Art with Mixed Motion Dynamics

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Animating Arbitrary Objects via Deep Motion Transfer

Official inference repo for FLUX.1 models

Source code for the SIGGRAPH 2024 paper "X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention"

[NeurIPS 2023] FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing

[NeurIPS 2023] Official implementation of the paper "Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset"