Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
- machine-learning
- convolutional-networks
- embedding-vectors
- embeddings
91,851 visible repositories in the index
241–264 of 847 · Most stars
Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
Pinry, a tiling image board system for people who want to save, tag, and share images, videos and webpages in an easy to skim through format. It's open-source and self-hosted.
Insane(ly slow but wicked good) PNG image optimization
Codex skill for converting slide images, PDFs, and image-based PPTX files into editable PowerPoint decks.
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
DDSP: Differentiable Digital Signal Processing
Accelerated deep learning R&D
Python 黑魔法手册
Efficient vision foundation models for high-resolution generation and perception.
An AI-powered file management tool that ensures privacy by organizing local texts, images. Using Llama3.2 3B and Llava v1.6 models with the Nexa SDK, it intuitively scans, restructures, and organizes files for quick, seamless access and easy retrieval.
Custom nodes pack for ComfyUI This custom node helps to conveniently enhance images through Detector, Detailer, Upscaler, Pipe, and more.
Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"
PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
OpenMMLab Self-Supervised Learning Toolbox and Benchmark
HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
A Repo For Document AI
基于manga-image-translator 实现的开源漫画AI翻译桌面工具。支持日、韩、英文漫画自动处理,集成OpenAl、Gemini等多翻译引擎;实现OCR文字检测、原文擦除、AI翻译、图像修复、译文排版完整链路,自带可视化编辑器,支持自定义文本样式,一键部署开箱即用。
OneTrainer is a one-stop solution for all your Diffusion training needs.
E-Ink Magic Calendar that automatically syncs to Google Calendar and runs off a battery powered Raspberry Pi Zero
The process of extracting product data from Amazon using Python, including titles, ratings, prices, images, and descriptions.
[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
This repository includes the official project of TransUNet, presented in our paper: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.
QualityScaler - image/video AI upscaler app
The Project is real time application in opencv using first order model