Ecosystem & Stack: cuda

A KVCache-centric disaggregated architecture for high-performance LLM serving, powering leading AI services.

A PyTorch-based framework to adapt Meta AI's Segment Anything Model (SAM) for improved performance on challenging downstream computer vision tasks using adapters and prompts.

A deep learning toolkit for training custom multimodal large language models focused on speech, language, audio, and music processing.

A beginner-friendly UI for fine-tuning language models using LoRA on commodity NVIDIA GPUs, though the project is no longer actively maintained.

A cost-effective solution for fine-tuning ChatGLM-6B using LoRA, enabling personalized large language models.

A multi-LoRA inference server designed to efficiently serve thousands of fine-tuned Large Language Models on a single GPU, drastically cutting serving costs while maintaining high throughput and low latency.

A modular PyTorch library for state-of-the-art diffusion models, enabling easy generation of images, audio, and more.

Extends ComfyUI with advanced custom nodes for the LTX-2 video generation model, enabling powerful text-to-video and image-to-video workflows.

Automates YouTube Shorts generation from long videos using AI for highlights, subtitles, and vertical cropping.

Generate high-quality audiobooks and voiceovers from various text formats with synchronized captions.

A powerful open-source web UI for few-shot voice conversion and text-to-speech, enabling high-quality voice cloning with minimal audio data.

vLLM-Omni is an efficient, flexible, and easy-to-use framework extending vLLM to serve omni-modality models (text, image, video, audio) with high throughput and an OpenAI-compatible API.

A comprehensive toolkit for fine-tuning ChatGLM-6B, ChatGLM2-6B, and ChatGLM3-6B models using various methods like Freeze, Lora, P-tuning, and full parameter fine-tuning.

A powerful AI-powered web application for comprehensive multimedia content creation, offering advanced speech recognition, voice cloning, multilingual TTS, and YouTube video processing.

Provides a local web interface and API for the ChatTTS model, enabling text-to-speech synthesis with support for mixed languages and numbers.

A user-friendly web-based tool for voice cloning, text-to-speech, and speech-to-speech conversion, leveraging the Coqui XTTS_v2 model with multi-language support.

DiffSinger is an official PyTorch implementation of a singing voice synthesis (SVS) and text-to-speech (TTS) system, leveraging a shallow diffusion mechanism for high-quality audio generation.

An open-source implementation of Microsoft's VALL-E X, enabling zero-shot multilingual text-to-speech synthesis and voice cloning with emotion control.

A cross-platform C#/.NET library for efficient local inference of large language models (LLMs) like LLaMA and LLAVA.

An all-in-one open-source WebUI for AI generative image and video creation, captioning, and processing, built on Stable Diffusion.

A comprehensive repository offering expert-level tutorials, guides, and courses on various Generative AI technologies, primarily focusing on Stable Diffusion and its ecosystem.

Create dynamic videos by smoothly transitioning between text prompts using Stable Diffusion's latent space exploration.

An extensive node suite that integrates cutting-edge 3D generation algorithms and models into ComfyUI, enabling seamless processing of 3D inputs like meshes and UV textures.