🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Free, open source crypto trading bot

State-of-the-art 2D and 3D Face Analysis Project

Backup and keep your application settings in sync.

Wan: Open and Advanced Large-Scale Video Generative Models

Enjoy the magic of Diffusion models!

Code for the paper Hybrid Spectrogram and Waveform Source Separation

Github.com/CryptoSignal - Trading & Technical Analysis Bot - 4,100+ stars, 1,100+ forks

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

ComfyUI's ControlNet Auxiliary Preprocessors

Download the entire Wayback Machine archive for a given URL.

ComfyUI Plugin of Nunchaku

💰 Cryptocurrency Trading Bot for Binance (Experimental)

pytorch implementation for "Deep Flow-Guided Video Inpainting"(CVPR'19)

Open-Set Grounded Text-to-Image Generation

Official SeedVR2 Video Upscaler for ComfyUI

The terminal command palette

A ComfyUI custom node designed for advanced image background removal and object, face, clothes, and fashion segmentation, utilizing multiple models including RMBG-2.0, INSPYRENET, BEN, BEN2, BiRefN…

Qwen-Image-Layered: Layered Decomposition for Inherent Editablity

Full-featured Python interface for the Slack API

[ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning

High quality training free inpaint for every stable diffusion model. Supports ComfyUI

Motion OPerators for Houdini, a motion graphics toolkit.

MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenario…

🐈 Render full tmux windows or individual panes as HTML

Image composition toolbox: everything you want to know about image composition or object insertion