Poisson disk sampling in arbitrary dimensions

Qwen-Image-Layered: Layered Decomposition for Inherent Editablity

Sharp Monocular View Synthesis in Less Than a Second

MCP server for OpenAI o3 web search

Open-Source Frontier Voice AI

Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embeddings and metadata.

SAM 3D Objects

Official Pytorch Implementation for "Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising"

Open-source vector similarity search for Postgres

Official implementation of ATI: Any Trajectory Instruction for Controllable Video Generation. https://arxiv.org/pdf/2505.22944

『推薦システム実践入門』のリポジトリ

Best Practices on Recommendation Systems

Instant Skinned Gaussian Avatars for Web, Mobile and VR Applications

Implementation of faceswap based on InstantID for ComfyUI.

Command Line Interface for Managing ComfyUI

😎 Finding duplicate images made easy!

Official repository for the paper "CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models"

A curated collection of fun and creative examples generated with Nano Banana & Nano Banana Pro🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the commu…

Intel One Mono font repository

Execution Time Analysis, Reroute Enhancement, Remote Python Logs, For ComfyUI developers.

a ComfyUI plugin that provides a user interface of AudioMass, full-featured web-based audio & waveform editing tool

Simultaneous speech-to-text model