Highlights
- Pro
Stars
Training and serving large-scale neural networks with auto parallelization.
A machine learning compiler for GPUs, CPUs, and ML accelerators
Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024
Standardized Serverless ML Inference Platform on Kubernetes
Python tool for converting files and office documents to Markdown.
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
WebUI extension for ControlNet
Repository for training models for music source separation.
Easy to use stem (e.g. instrumental/vocals) separation from CLI or as a python package, using a variety of amazing pre-trained models (primarily from UVR)
A WebUI app for Music-Source-Separation-Training and we packed UVR together!
Gradio UI for running Meta AI's Segment Anything on own hardware. Promptable segmentation via keypoints and bounding boxes.
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Segment Anything (SAM) at Home web app using Gradio
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models.
Python Binding for waifu2x-ncnn-vulkan with PyBind11
Pytorch implementation of FTNet for Semantic Segmentation on SODA, SCUT Seg, and MFN Datasets
ICRA 2020 | Repository for "PST900 RGB-Thermal Calibration, Dataset and Segmentation Network" | C++, Python, PyTorch
A set of Python scripts to evaluate the Automotive Datasets provided by Prophesee
This is the official code release for our work, Denoising Vision Transformers.
A bepinex mod to enhance game experience (maybe)
Lightning fast C++/CUDA neural network framework
ImageNet-R(endition) and DeepAugment (ICCV 2021)
A Python package mapping 2D coordinates to colors based on different 2D color maps.