HunyuanVideo: A Systematic Framework For Large Video Generation Model
- video-generation
- diffusion-models
- diffusion-transformer
47,133 repositories indexed
121–144 of 546 · Most stars
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Access large language models from the command-line
Hierarchical Reasoning Model Official Release
The ultimate training toolkit for finetuning diffusion models
A collection of resources and papers on Diffusion Models
An open-source, tool-augmented conversational language model from Fudan University
A command-line productivity tool powered by AI large language models like GPT-5, will help you accomplish your tasks faster and more efficiently.
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
OCR & Document Extraction using vision models
The official GitHub page for the survey paper "A Survey of Large Language Models".
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
Foundational Models for State-of-the-Art Speech and Text Translation
Low-code framework for building custom LLMs, neural networks, and other AI models
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Statsmodels: statistical modeling and econometrics in Python
Reference PyTorch implementation and models for DINOv3
The quip network mining stack. This includes a coordinator and links all of the official quip network miners.
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
Official repository for LTX-Video
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
Refine high-quality datasets and visual AI models
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.
Enable Opencode to authenticate against Antigravity (Google's IDE) via OAuth so you can use Antigravity rate limits and access models like gemini-3-pro and claude-opus-4-5-thinking with your Google credentials.