Open-source projects tagged “pytorch”

A lightweight zipvoice-based text-to-speech model for voice cloning, generating 48kHz speech at up to 150x realtime on GPU.

Training, generation and utility scripts for Stable Diffusion and other image generation models, covering LoRA and fine-tuning.

Python inference library for Kokoro-82M, an open-weight text-to-speech model with 82 million parameters.

Open-source large video generative models that create videos from text, images, speech, or character motion, with MoE and 720P options.

A Gradio-based web UI for running Stable Diffusion and newer image/video models, continuing the Forge fork of AUTOMATIC1111's WebUI.

A node-graph GUI, API and backend for running diffusion models to generate images, video, audio and 3D locally.

Open-source model from Tencent Hunyuan that generates interactive game videos from a reference image and keyboard or mouse inputs.

Open-source toolkit from Unity that lets games and simulations serve as environments for training AI agents with reinforcement and imitation learning.

A unified training engine for multimodal models, supporting vision-language, diffusion, and MoE architectures with FSDP2, Muon, and Liger kernels.

A video LLM trained with streaming speech transcription so it can produce real-time commentary on video, with Gradio and CLI demos.

Open-source framework for real-time, audio-driven avatar video generation that streams with effectively unlimited length, built on a 14B Wan2.2-S2V base model.

A PyTorch-based blind face restoration model that repairs degraded, low-quality, or old face photos using a codebook lookup transformer.

A short introductory book on reinforcement learning, with PyTorch implementations of the algorithms it covers from MC to PPO.

A Python library for document AI that combines layout analysis, table recognition, OCR and document or token classification into configurable pipelines.

A cross-platform desktop app for upscaling images with built-in or custom super-resolution models, supporting Windows, macOS, and Linux.

An open-source Python OCR library that detects and recognizes text in PDFs and images using deep learning models built on PyTorch.

A 12-chapter, commented tutorial that walks through building and training a LLaMA-style GPT language model from scratch in Python and PyTorch.

CLI tool to fine-tune and post-train LLMs from a single YAML config, with layer streaming for training 8B models on a 4 GB GPU.

A local-first browser automation engine and Agent Skill that runs Qwen3.5 models on-device to pick browser actions from visible page elements.

Ultra-lightweight on-device text-to-speech model with an 80M-parameter architecture, streaming output at 32kHz, and CPU, CUDA and MPS support.