Implementation of Parti, Google's pure attention-based text-to-image neural network, in Pytorch

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

Large Concept Models: Language modeling in a sentence representation space

A much modified lyric editor with fancy (maybe) UI based on WPF

一个输入法状态实时提示工具。An input method status tip tool.

Kandinsky 2 — multilingual text2image latent diffusion model

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

Windows动态修改鼠标指针光标颜色图标样式, 根据键盘布局/语言/输入法的切换而变化. Change cursor/pointer style/color dynamically base on Keyboard Layout/Input Locale/IME/Language on Windows.

🎛 🔊 A Python library for audio.

思源笔记模版Me 包含一些基础模板。另添加了234张高清4K带鱼屏图片和live2d动画人物+音乐播放器模板

A dictionary for Montreal-Forced-Aligner users to align mandarin data labeled in pinyin form using the mfa pretrained model v2.0.

An all-purpose window upscaler for Windows 10/11.

Command line utility for forced alignment using Kaldi

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

🪄 VS Code Theme Elaina

ImTip 智能桌面助手：仅 820 KB，提供输入跟踪提示 + 超级热键，可将各种桌面应用快速接入 AI 大模型

防止微软拼音输入法启动切换到英文模式

Sprites video data used in the ICML 2018 paper

Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Python audio and music signal processing library

[CVPR2019]Learning Not to Learn : An adversarial method to train deep neural networks with biased data

SVHN dataset preprocessing and annotation file reading and converting python library

Re-editable LaTeX/ typst graphics for Inkscape

Stable Diffusion web UI

Let us control diffusion models!

sketch + style = paints 🎨 (TOG2018/SIGGRAPH2018ASIA)

Research code for pixel-based encoders of language (PIXEL)

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

A Python wrapper for Google Tesseract