Training Sparse Autoencoders on Language Models

🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

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

Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

LLM inference in C/C++

A fast inference library for running LLMs locally on modern consumer-class GPUs

Tools for merging pretrained large language models.

A self-ailgnment method for role-play. Benchmark for role-play. Resources for "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment".

The definitive Web UI for local AI, with powerful features and easy setup.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

A User Interface for XTTS-2 Text-Based Voice Cloning using only 10 seconds of speech

Instant voice cloning by MIT and MyShell. Audio foundation model.

a little engine for little games, worlds, and stories

AI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, plans, executes, and iterates until it achieves a successful result.

Orcus is a retro-clone of 4th Edition

RSS reader in go on app engine; formerly goread.io

Universal and Transferable Attacks on Aligned Language Models

Gaming meets modern C++ - a fast and reliable entity component system (ECS) and much more

Stable Diffusion web UI

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

VITS-based zero-shot TTS system varying with diverse style/speaker conditioning methods.

TransferTTS (Zero-Shot learning of VITS)

🔊 Text-Prompted Generative Audio Model

🔊 Text-prompted Generative Audio Model - With the ability to clone voices

A fully working pytorch implementation of NaturalSpeech (Tan et al., 2022)

YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

The Glulx VM reference interpreter