PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

A character-level language diffusion model trained on Tiny Shakespeare

Fully automatic censorship removal for language models

The ultimate training toolkit for finetuning diffusion models

The best ChatGPT that $100 can buy.

Generative models for conditional audio generation

State-of-the-art TTS model under 25MB 😻

https://hf.co/hexgrad/Kokoro-82M

Text-audio foundation model from Boson AI

Dear ImGui: Bloat-free Graphical User interface for C++ with minimal dependencies

Converts noisy high resolution pixel art such as pixel art images created by LLMs to true resolution.

The GPT-4o image generation we have at home. A powerful, self-hosted AI photo stylizer built for performance and privacy.

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Generate character consistent images with a single reference

A scalable abstraction learning library

Crawler for Amiga Music Preservation (AMP) site

FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

Automating Music Generation via simple music informed algorithm!

The official code implementation of the paper "OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data."