用于安卓 GKD 的第三方订阅规则 (👻Fork版)

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

张雪峰.skill — 张雪峰的认知操作系统。高考志愿/考研/职业规划的实战思维框架。由女娲.skill生成。

Very customizable imageboard/booru downloader with powerful filenaming features.

Multi functional app to find duplicates, empty folders, similar images etc.

"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"

CLI / Function call / API server to manager Runpod Network Volume Storage

Fork of SageAttention for Windows wheels and easy installation

Awesome curated collection of images and prompts generated by z-image-turbo state-of-the-art open-source image generation and editing model.

分享一下自创以及打野得到的各种优质prompt

Run LLM/VLM models natively in ComfyUI based on llama.cpp

Another comfy implementation for the short video generation project hpcaitech/Open-Sora, supporting latest V2 and V3 models as well as image to video functions, etc.

LLM Frontend for Power Users.

Python bindings for llama.cpp

An API endpoint that supports Qwen3-VL image understanding and video understanding.

The Excalibur of Hyper-V / Hyper-V 神器

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Simple DepthAnythingV2 inference node for monocular depth estimation

Inference Microsoft Florence2 VLM

ComfyUI nodes for SCAIL-Pose preprocessing

SUPIR upscaling wrapper for ComfyUI

A custom node for ComfyUI that dynamically manages RAM usage by intelligently controlling cache purging based on available system memory.

ComfyUI wrapper for segment anything 3

SDPose-OOD的comfyui节点。implementation of SDPose-OOD in ComfyUI

A simple node that can dynamically adjust the reserved memory of a workflow in real-time, used to avoid the utilization of shared memory.

A ComfyUI node that could help you batch process files

The goal is to make it easier to configure your favorite Linux distribution as a router. Built with Rust and eBPF.

A ComfyUI node for dvlab-research/DreamOmni2