Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs

Dota 2 Ability Draft Live overlay to improve your drafting skills.

Draw animated Japanese characters (Kanji and Kana), Korean characters (Hanja) and Chinese characters (Hanzi) in correct stroke order using svg, free open-source code.

Opensource software for the Landzo Quincy Drawing Robot Artist

Pytorch implementation of VQGAN (Taming Transformers for High-Resolution Image Synthesis) (https://arxiv.org/pdf/2012.09841.pdf)

Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.

Official PaddlePaddle Implementation of Few-Shot Font Generation by Learning Fine-Grained Local Styles (FsFont)

A short description of the project. This Repository will demonstrate using Pytorch to build deep convolutional neural networks and use Qt to create the GUI with the pre-trained model.

甲骨文（oracle bone script）汉字对照表数据库，提供 Json，Sqlite

Oracle Character Recognition Dataset - Oracle-50K

[Multimedia Systems] SiamHCC: a novel siamese network for quality evaluation of handwritten Chinese characters

Official implementation of VQ-Diffusion

DQ風のステッカーが作れます

Learn Chinese on the go - no Internet connection required!

ASCII generator (image to text, image to image, video to video)

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

颜真卿书法家楷书风格的书法汉字图像数据集，图像数共计856张，已开源。

[AAAI2024] Official PyTorch implementation of VQ-Font: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization.

FSL-Mate: A collection of resources for few-shot learning (FSL).

Tesla Light Show

YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.

Han character library for CJKV languages

Free, open-source Chinese character data

PyTorch implementation of VQ-VAE by Aäron van den Oord et al.

[ICCV 2023] Few shot font generation via transferring similarity guided global and quantization local styles