A Conversational Speech Generation Model

Wan: Open and Advanced Large-Scale Video Generative Models

Official code for AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset

Weather forecasting with Deep Learning

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

SAM 3D Objects

Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Lets make video diffusion practical!

Image editing is worth a single LoRA! 0.1% training data and 1% training parameters for fantastic image editing! Surpasses GPT-4o in ID persistence! Only 4GB VRAM is enough to run!

Official Implementation of Tangential Amplifying Guidance

python module for CATIA V5 automation

Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property c…

[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat

Download numerical weather prediction datasets (HRRR, RAP, GFS, IFS, etc.) from NOMADS, NODD partners (Amazon, Google, Microsoft), ECMWF open data, and the University of Utah Pando Archive System.

The open-source solutions of FourCastNet and GraphCast

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

Proof-of-concept implementation of the Agentic Context Engineering (ACE) framework — demonstrating Generator-Reflector-Curator interactions for self-improving LLMs on the HotpotQA dataset.

Replace 'hub' with 'ingest' in any github url to get a prompt-friendly extract of a codebase

ComfyUI-SparkTTS is a custom ComfyUI node implementation of SparkTTS, an advanced text-to-speech system that harnesses the power of large language models (LLMs) to generate highly accurate and natu…

Official custom nodes for using Tripo in ComfyUI.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching

RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Witness the aha moment of VLM with less than $3.

HunyuanVideo: A Systematic Framework For Large Video Generation Model