A Blood Glucose data visualization tool.

A collection of 🤗 Transformers.js demos and example applications

Full in-browser Semantic Search with Huggingface Transformers.js and ElectricSQL's PGlite!

Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

yoflo-like implementation of the smolVLM series

Use LLMs in Excel formulas

A Lightweight Recommendation System

A publishing platform for apps developed by the Tidbyt community 🚀

SDK & API Docs Generator. Sunset as of December 2024

LLM-powered multiagent persona simulation for imagination enhancement and business insights.

🌊 Images to → 3D Parallax effect video. A free and open source ImmersityAI alternative

The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.

CLIP+MLP Aesthetic Score Predictor

An onboarding wizard flow / product tour for Next.js animated by framer motion

A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Dead simple FLUX LoRA training UI with LOW VRAM support

[ECCV 2024] The official code of paper "Open-Vocabulary SAM".

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

📨 The ultimate social media scheduling tool, with a bunch of AI 🤖

A command-line tool to download photos from iCloud

Various AI scripts. Mostly Stable Diffusion stuff.

Quick exploration into fine tuning florence 2

Finding A Time is a simple tool that helps you schedule meetings with your team, friends or clients.

real time face swap and one-click video deepfake with only a single image

fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

Official Implementation of "Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining"

cables is a tool for creating beautiful interactive content