tiny vision language model

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Unofficial implementation of InstantID for ComfyUI

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

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

LLM inference in C/C++

Foundational Models for State-of-the-Art Speech and Text Translation

XTTSv2 Extension for oobabooga text-generation-webui

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Industry leading face manipulation platform

A framework to enable a multimodal model to operate a computer.

ComfyUI related stuff and things

Interact privately with your documents using the power of GPT, 100% privately, no data leaks

Google's SoundStorm: Efficient Parallel Audio Generation

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

🎥 Python and OpenCV-based scene cut/transition detection program & library.

Interact with your documents using the power of GPT, 100% privately, no data leaks

Official Code for DragGAN (SIGGRAPH 2023)

Code for GAN2Shape (ICLR2021 oral)

FLUX, Stable Diffusion, SDXL, SD3, LoRA, Fine Tuning, DreamBooth, Training, Automatic1111, Forge WebUI, SwarmUI, DeepFake, TTS, Animation, Text To Video, Tutorials, Guides, Lectures, Courses, Comfy…

BabyAGI to run with GPT4All

Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

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

🔊 Text-Prompted Generative Audio Model