发布

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

ComfyUI nodes for SCAIL-Pose preprocessing

[NeurIPS 2024] Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation

Offical Implementation of SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations

[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

The official repo for "Vidi: Large Multimodal Models for Video Understanding and Editing"

An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.

Main TurboVNC repository

Lightweight coding agent that runs in your terminal

This is an AI agent for Street Fighter II Champion Edition.

interactive visualization of 5 popular gradient descent methods with step-by-step illustration and hyperparameter tuning UI

A custom node for ComfyUI designed to facilitate the real-time transmission of rendered images, videos, 3D models or audio to TouchDesigner.

Capture Webcamera and URL media streams as ComfyUI images

ComfyUI Nodes for using Spout streams

ComfyUI Depth Anything (v1/v2/distill-any-depth) Tensorrt Custom Node (up to 14x faster)

A ComfyUI custom node for running real-time media workflows directly within ComfyUI, enabling seamless AI-powered video and audio processing.

Run Comfy workflows on video streams

问答基准测试集是实验编程（code-2-art）社群开发的独特数据集，旨在评估人工智能模型在实际应用场景中的问答能力。与传统基准测试不同，这些数据集强调实用性和创造性，而非标准化评估。

ComfyUI custom nodes and web utilities for real-time AI generation and interaction

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

Easily set Mac Retina display to higher unsupported resolutions

Kolosal AI is an OpenSource and Lightweight alternative to LM Studio to run LLMs 100% offline on your device.

HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

Open source interactive livestream for twitch!

Open-Sora: Democratizing Efficient Video Production for All

SkyReels-V2: Infinite-length Film Generative model

Wan: Open and Advanced Large-Scale Video Generative Models