Stars
HyperMotion is a pose guided human image animation framework based on a large-scale video diffusion Transformer.
Mapping Mediapipe's 52 blendshapes to FLAME's expression coefficients and poses.
A list of works on video generation towards world model
An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Training released! Surpasses GPT-4o in ID persistence! Official ComfyUI workflow release! Only 4GB VRAM is enou…
Collection of the latest spatial, 3D, and video/temporal reasoning papers
Code for "Steerable Scene Generation with Post Training and Inference-Time Search"
Roblox Foundation Model for 3D Intelligence
State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!
code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"
A curated list of awesome 3D scene generation papers. (arXiv 2505.05474)
Code&Data for Grounded 3D-LLM with Referent Tokens
Generative AI for Character Animation: A Comprehensive Survey of Techniques, Applications, and Future Directions
Code for paper "Towards Understanding Camera Motions in Any Video"
[CVPR 2025] A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
RepText: Rendering Visual Text via Replicating 🔥
UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
A lightweight, powerful framework for multi-agent workflows
MAGI-1: Autoregressive Video Generation at Scale
[ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
🚀🚀🚀A curated list of papers on controllable video generation.
Lets make video diffusion practical!