Free universal database tool and SQL client

[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs

HTTP load testing tool and library. It's over 9000!

Legend Motion is a declarative animations library for React Native, to make it easy to transition between styles without needing to manage animations.

Provides a modified port of Douglas Crockford's jsmin.c, which removes unnecessary whitespace from JavaScript files.

A website to scrape? There's a simple way.

LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

Face detection and recognition framework

Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections.

[ECCV2024] ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation

CSS loading animations with minimal effort!

AutoMQ is a cloud-first alternative to Kafka by decoupling durability to S3 and EBS. 10x cost-effective. Autoscale in seconds. Single-digit ms latency.

Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

A JavaScript library like PyTorch, with GPU acceleration.

A lightweight emoji picker for the modern web

[ICCV 2023] Text2Tex: Text-driven Texture Synthesis via Diffusion Models

Official pytorch implementation of "XHand: Real-time Expressive Hand Avatar"

A JavaScript library to position floating elements and create interactions for them.

SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement

Tensor parallelism is all you need. Run LLMs on an AI cluster at home using any device. Distribute the workload, divide RAM usage, and increase inference speed.

Official inference repo for FLUX.1 models

AmebaPro2 Arduino third-party package SDK

Async Web Server for ESP8266 and ESP32

An implementation of Shazam's song matching algorithm.

DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization (ICLR2024) & DynaVol-S: Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering

Scan, Connect, Write, Read with Ble device in Andoid background

Official implementation for HybridDepth Model