Stars
An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)
⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Factory / ms-swift / U…
[ICML 2025] The official implementation of the paper "On the Guidance of Flow Matching"
CircuitNet: An Open-Source Dataset for Machine Learning Applications in Electronic Design Automation (EDA)
XR Animator, AI-based Full Body Motion Capture and Extended Reality (XR) solution, powered by System Animator Online
Mod / Plugin for KK / KKS to export Characters into PMX Format and additional Utility to cleanup the model into a useable state for MMD
Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"
[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Custom Dance Player mod for Mate Engine
A free Desktop Mate alternative with a lightweight interface and custom VRM support, though with more features.
集找番、追番、看番的一站式弹幕追番平台，云收藏同步 (Bangumi)，离线缓存，BitTorrent，弹幕云过滤。100% Kotlin/Compose Multiplatform
MCP 资源精选， MCP指南，Claude MCP，MCP Servers, MCP Clients
An open protocol enabling communication and interoperability between opaque agentic applications.
A brief review of 2023 NJUAI open day test & interview
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
A summary of related works about flow matching, stochastic interpolants
Implement different schedulers for flow matching models
Diffusion Model Experiment: Fitting an Elliptical Distribution, Flow Matching Proves More Efficient than DDPM The experiment compares training efficiency and sampling trajectories between DDPM (tra…
TorchCFM: a Conditional Flow Matching library
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.
Implementation of Flow Matching model for MNIST to understand how it works
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.