OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation [SIGGRAPH 2025]

CADAM is the open source text-to-CAD web application

A unified inference and post-training framework for accelerated video generation.

[ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds

Official implementation of Inductive Moment Matching

Here you'll find a growing collection of 3D models, textures, and images from inside NASA.

Official code for paper: Scaling Mesh Generation via Compressive Tokenization [CVPR'25]

High-Performance SGEMM on CUDA devices

A generative world for general-purpose robotics & embodied AI learning.

[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

a cpp ggml port of "VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech." for use in mobile devices. this is my undergraduate project

Zero-Shot Speech Editing and Text-to-Speech in the Wild

lightweight, standalone C++ inference engine for Google's Gemma models.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

An Open Source text-to-speech system built by inverting Whisper.

Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.

The first real AI developer

A library to inspect and extract intermediate layers of PyTorch models.

VITS implementation of Japanese, Chinese, Korean, Sanskrit and Thai

Turn expensive prompts into cheap fine-tuned models

Finetune a LLM to speak like you based on your WhatsApp Conversations

Mimic Recording Studio is a Docker-based application you can install to record voice samples, which can then be trained into a TTS voice with Mimic2

Local voice recording for creating Piper datasets

An extensible, easy-to-use, and portable diffusion web UI 👨‍🎨

fmemopen on windows

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

SoftVC VITS Singing Voice Conversion