Stars
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
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.
Neural Style Transfer For Chinese Characters, implemented in Tensorflow 2, with custom dataset.
The unified repository for few-shot font generation methods. This repository includes FUNIT (ICCV'19), DM-Font (ECCV'20), LF-Font (AAAI'21) and MX-Font (ICCV'21).
CalliGAN - Tensorflow Implementation (AI for Content Creation Workshop CVPR 2020)
Learning Chinese Character style with conditional GAN
TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis
Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>
Calligrapher: Freestyle Text Image Customization
自动视频生成器，给定主题，自动生成解说视频。用户输入主题文字，系统调用大语言模型生成故事或解说的文字，然后进一步调用语音合成接口生成解说的语音，调用文生图接口生成契合文字内容的配图，最后融合语音和配图生成解说视频。
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
End-to-end realtime stack for connecting humans and AI
Android V1 and V2 Signature Channel Package Plugin
An open image dataset for cursive Chinese calligraphy text.
Official mirror of Rubber Band Library, an audio time-stretching and pitch-shifting library.
Software synthesizer based on the SoundFont 2 specifications / This is a really dumb patchset to remove glib as a dependency.
A lightweight, customizable Vue UI library for mobile web apps.
YouTube Player library for Android and Chromecast, stable and customizable.
Lightweight helper library that allows iOS developers to add inline playback of YouTube videos through a WebView
Compile openssl and curl for Android
A blank iOS app build system written in CMake. Includes building a dynamically linked C++ framework and bundling it into the app.
Android Bluetooth Low Energy (BLE) Fast Development Framework. It uses simple ways to filter, scan, connect, read ,write, notify, readRssi, setMTU, and multiConnection.
Optical Music Recognition dataset for handwritten annotations in music scores of the long 19th century.
Converts Lottie Animations (.json / .lottie) and Telegram stickers (*.tgs) to GIF / PNG / APNG / WEBP / WEBM