lucasjinreal

yt-dlp

A feature-rich command-line audio/video downloader

GPTs

leaked prompts of GPTs

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

AnimateAnyone

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

Awesome-Chinese-LLM

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

self-operating-computer

A framework to enable multimodal models to operate a computer.

clone-voice

A sound cloning tool with a web interface, using your voice or any sound to record audio / 一个带web界面的声音克隆工具，使用你的音色或任意声音来录制音频

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

inpaint-web

A free and open-source inpainting & image-upscaling tool powered by webgpu and wasm on the browser。| 基于 Webgpu 技术和 wasm 技术的免费开源 inpainting & image-upscaling 工具, 纯浏览器端实现。

Video-LLaVA

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

llm-awq

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

T-Rex

API for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

aidea-server

AIdea 是一款支持 GPT 以及国产大语言模型通义千问、文心一言等，支持 Stable Diffusion 文生图、图生图、 SDXL1.0、超分辨率、图片上色的全能型 APP。

sd-webui-depth-lib

Depth map library for use with the Control Net extension for Automatic1111/stable-diffusion-webui

ComfyUI-Impact-Pack

Custom nodes pack for ComfyUI This custom node helps to conveniently enhance images through Detector, Detailer, Upscaler, Pipe, and more.

AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

LookaheadDecoding

was-node-suite-comfyui

An extensive node suite for ComfyUI with over 210 new nodes

efficiency-nodes-comfyui

A collection of ComfyUI custom nodes.- Awesome smart way to work with nodes!

LLM-Shearing

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

GigaGAN

openai-proxy

openai-proxy is a solution provided for Chinese users to address the issue of being unable to make requests to the OpenAI API.

super_native_extensions

Native drag & drop, clipboard access and context menu.

Shush

Shush is an app that deploys a WhisperV3 model with Flash Attention v2 on Modal and makes requests to it via a NextJS app

awesome-comfyui

An awesome & curated list of cool tools for ComfyUI.

avatarstudio

AvatarStudio: High-fidelity and Animatable 3D Avatar Creation from Text

CustomChar

Your customized AI assistant - Personal assistants on any hardware! With llama.cpp, whisper.cpp, ggml, LLaMA-v2.

arxiv-frontpage

My personal frontpage app

PowerNoiseSuite

Power Noise Suite for ComfyUI is a latent noise oriented custom_node for variation in your generations

PyTorch-Conference-notes

有关 PyTorch Conference 的全会议中文转录摘要，结构化笔记