The Smallest English TTS Model with only 1M parameters

Soprano: Instant, Ultra-Realistic Text-to-Speech

TRELLIS (Microsoft's Image-to-3D generator) running on AMD GPUs with ROCm. Includes Gaussian splatting, mesh extraction, and GLB export. Tested on RX 7800 XT.

A high quality and fast TTS repository

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

A Modular Framework for 3D Generation and Beyond [WIP]

Spark-TTS Inference Code

[CVPR 2025] Official repository for "Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders"

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

DEX-TTS: Diffusion-based EXpressive TTS with Style Modeling on Time Variability

Foundational model for human-like, expressive TTS

High-quality Text-to-Audio Generation with Efficient Diffusion Transformer

Hackable and optimized Transformers building blocks, supporting a composable construction.

TripoSR: Fast 3D Object Reconstruction from a Single Image

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

AMD (Radeon GPU) ROCm based setup for popular AI tools on Ubuntu 26.04

Godot's AdMob Plugin for Android with support for Mediations.

Shader for Blender attempting to replicate the shading of Genshin Impact. These are for datamined assets, not custom-made ones nor the MMD variants.

Procedural Anime Assets

A CLI to export a GDevelop Game without the IDE with plugins support.