TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Pythonic bindings for FFmpeg's libraries.

Lets make video diffusion practical!

A curated list of papers on reinforcement learning for video generation

Audio synthesis, processing, & analysis platform for iOS, macOS and tvOS

[ACM MM 2025] Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis

Daily tracking of awesome avatar papers, including 2d talking head, 3d head avatar, body avatar.

📖 A curated list of resources dedicated to talking face.

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

Light Video Generation Inference Framework

LTX-Video Support for ComfyUI

Enjoy the magic of Diffusion models!

[SIGGRAPH Asia 2025] Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization

SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs

Solve Visual Understanding with Reinforced VLMs

[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

Official repository of In-Context LoRA for Diffusion Transformers

Official implementation of "JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization"

Wan: Open and Advanced Large-Scale Video Generative Models

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis