Hugging Face – The AI community building the future.

The platform where the machine learning community collaborates on models, datasets, and applications.
A hands-on guide to training Mixture-of-Experts models
Which coding-agent harness should you use for your model?
generate a video from an image with a text prompt
Uncensored Qwen-Image-2.1 generate + edit
Generate a video animation from a single image and prompt
Create, discover and collaborate on ML better.
Host and collaborate on unlimited public models, datasets and applications.
With the HF Open source stack.
Text, image, video, audio or even 3D.
Share your work with the world and build your ML profile.
We provide paid Compute and Enterprise solutions.
Give your team the most advanced platform to build AI with enterprise-grade security, access controls and dedicated support.
Starting at $20/user/month
Access 45,000+ models from leading AI providers through a single, unified API with no service fees.
Deploy on optimized Inference Endpoints or update your Spaces applications to a GPU in a few clicks.
Starting at $0.60/hour for GPU
We are building the foundation of ML tooling with the community.
State-of-the-art AI models for PyTorch
State-of-the-art Diffusion models in PyTorch
Safe way to store/distribute neural network weights
Python client to interact with the Hugging Face Hub
Fast tokenizers optimized for research & production
Train transformers LMs with reinforcement learning
State-of-the-art ML running directly in your browser
Smol library to build great agents in Python
Parameter-efficient finetuning for large language models
Access & share datasets for any ML tasks
Making AI for Robotics more accessible with end-to-end learning
Train PyTorch models with multi-GPU, TPU, mixed precision