The official code repository for LeVo: High-Quality Song Generation with Multi-Preference Alignment

Custom nodes for ComfyUI to enable flow control with advanced loops, conditional branching, logic operations and several other nifty utilities to enhance your ComfyUI workflows

Generative grammars for the PrestoPlot tool: https://github.com/eykd/prestoplot/

[Preprint 2025] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

Visual node-based AI image captioning tool with various AI models. Customizable pipelines, real-time processing, metadata export.

Fast and memory-efficient exact attention

Extended Musubi Tuner with latent previews, fp16 accumulation, advanced cfg scheduling and more

This is the official implementation of our Señorita-2M [Weights and Dataset] : A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists

Custom nodes that bring Character.AI's Ovi video+audio generator to ComfyUI with streamlined setup, selectable precision, attention-backend control, and per-node device targeting for multi-GPU rigs.

ArduPlane, ArduCopter, ArduRover, ArduSub source

This project showcases a series of code (mainly Python) towards creating an autonomous drone using Raspberry Pi Pico. This project also showcases hardware set-up: microcontroller (Raspberry Pi Pico…

Woobu Autonomous Drone is a flying machine project. Code Completed. This project uses Raspberry Pi Pico plus MPU6050 as main hardware, and (Micro)Python, HTML and JavaScript as the main programming…

StratoSoar MK3, an autonomous glider meant for high-altitudes, accessible to everyone

🔥 ComfyUI-OneAPI: Transform Complex Multi-Step Workflow API Calls → Just One API | 工作流极简化API调用

Nodes for using ComfyUI as a backend for external tools. Send and receive images directly without filesystem upload/download.

[SIGGRAPH-ASIA 2025] Official implementation of "VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models"

A pipeline parallel training script for diffusion models.

A unified inference and post-training framework for accelerated video generation.

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

VRM hand tracking using mediapipe

Open source web based custom VRM avatar creation platform

ComfyUI extension that enables multi-GPU processing locally, remotely and in the cloud

This custom_node for ComfyUI adds one-click "Virtual VRAM" for any UNet and CLIP loader as well MultiGPU integration in WanVideoWrapper, managing the offload/Block Swap of layers to DRAM *or* VRAM …

Feed-forward model for predicting 3D physics with 3DGS + NeRF

🔥🔥 Open-sourced unified customization model

Robust realtime face and facial landmark tracking on CPU with Unity integration