lucasgelfond / webgpu-sam2
Segment Anything 2, 100% in the browser (with WebGPU!)
☆127Updated 4 months ago
Alternatives and similar repositories for webgpu-sam2:
Users that are interested in webgpu-sam2 are comparing it to the libraries listed below
- Gradio UI for a Cog API☆67Updated last year
- kokoro text to speech using javascript☆55Updated 2 months ago
- In-browser LLM website generator☆49Updated 2 months ago
- A streamlined implementation of Grounding DINO and SAM for advanced image segmentation. This lightweight solution simplifies the integrat…☆63Updated 6 months ago
- Simple LaMa Inpainting: An easy-to-use implementation of the LaMa (Large Mask) inpainting model. Remove unwanted objects or fill in missi…☆22Updated 5 months ago
- ☆36Updated 2 months ago
- Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"☆77Updated 6 months ago
- Use the Moondream 2 model to detect faces and their gaze directions in videos.☆39Updated 3 months ago
- Cog inference for flux models☆343Updated last week
- A Next.js app for fast image generation with Flux on Replicate☆107Updated 6 months ago
- A demo for running comfy deploy api via nextjs☆167Updated last year
- Demonstration of MobileSAM in the browser enabled through ONNX runtime web☆106Updated last year
- Add local LLMs to your Web or Electron apps! Powered by Rust + WebGPU☆102Updated last year
- fast state-of-the-art speech models and a runtime that runs anywhere 💥☆55Updated 2 months ago
- OpenAI's CLIP model ported to JavaScript using the ONNX web runtime☆148Updated last year
- A PoC to run Segment Anything Model (SAM) entirely in the browser without any backend☆70Updated last year
- An OpenAI API compatible API for chat with image input and questions about the images. aka Multimodal.☆250Updated last month
- Useful resources for LLM-based Diarization and Transcription.☆55Updated 6 months ago
- ☆39Updated 3 weeks ago
- EntityDB is an in-browser vector database wrapping indexedDB and Transformers.js over WebAssembly☆149Updated 3 months ago
- This project is a reverse-engineered version of Figma's tone changer. It uses Groq's Llama-3-8b for high-speed inference and to adjust th…☆89Updated 8 months ago
- 2D-to-3D image generator and viewer: https://tiefling.app☆78Updated 2 months ago
- Using the moondream VLM with optical flow for promptable object tracking☆52Updated last month
- ☆47Updated 5 months ago
- Doodle Dash, an ML-powered web game that runs completely in your browser, thanks to Transformers.js!☆60Updated last year
- Run Large-Language Models (LLMs) 🚀 directly in your browser!☆192Updated 7 months ago
- ☆79Updated this week
- A client side vector search library that can embed, store, search, and cache vectors. Works on the browser and node. It outperforms OpenA…☆197Updated 10 months ago
- A JavaScript implementation of Llama 3 using node-mlx.☆72Updated 9 months ago
- Benchmarking Vision-Language Models on OCR tasks in Dynamic Video Environments☆37Updated 2 months ago