A series of simple function nodes made by myself are used to solve the problems I encounter in my daily use of comfyui.

A ComfyUI integration to use LMStudio for extending prompts.

Fork of SageAttention for Windows wheels and easy installation

A batch file to install the latest ComfyUI, make a venv within it and automatically install Triton and SageAttention for Hunyaun etc workflows.

Creates prompts for Video Models by sequence analysis and prompting using Qwen2.5-VL models from Alibaba.

A set of nodes to edit videos using the Hunyuan Video model

MoBA: Mixture of Block Attention for Long-Context LLMs

A generalist Python node editor

This project is a digital human that can talk to you and is animated based on your questions. It uses the Nvidia API endpoint Meta llama3-70b to generate responses, Eleven Labs to generate voice an…

Local LLM as a Service

Fully local web research and report writing assistant

AudioLatentNodes

Official repository for LTX-Video

This custom_node for ComfyUI adds one-click "Virtual VRAM" for any GGUF UNet and CLIP loader, managing the offload of layers to DRAM or VRAM to maximize the latent space of your card. Also includes…

Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The …

A beautiful theme extension for ComfyUI that adds festive touches with dynamic backgrounds, snowfall effects, and animated node connections

Non functional dev repo

This repository is a collection of ComfyUI nodes and workflows that can facilitate the creation of animations and video compilations. It will be updated from time to time.

Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

A port of muerrilla's sd-webui-Detail-Daemon as a node for ComfyUI, to adjust sigmas that control detail.

A blender add-on to use diffusion models for texture generation

Convert Mixamo animations directly to OpenPose image sequences