comfyui

Name: comfyui
Availability: InStock
Author: rickyananda

Automate ComfyUI setup, workflow execution, and output retrieval.

1|Updated May 18, 2026

Search Tags:#workflow automation #image generation #custom nodes #video generation #comfyui #stable diffusion

Ready to run

npx skills add https://github.com/rickyananda/hermes-skills --skill comfyui-rickyananda

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/rickyananda/hermes-skills/tree/main/creative/comfyui
Command: npx skills add https://github.com/rickyananda/hermes-skills --skill comfyui-rickyananda

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, websocket-client, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill removes the setup and orchestration burden of ComfyUI so you can generate media without manually managing nodes, models, queues, or output downloads.

Core Features & Use Cases

Install, launch, and verify ComfyUI locally or through Comfy Cloud.
Run API-format workflows for text-to-image, img2img, inpainting, upscaling, animation, audio, video, and 3D generation.
Inspect workflow parameters, check missing dependencies, upload input images, monitor execution, and download results safely.
Use it to swap prompts, seeds, checkpoints, LoRAs, and image inputs across reusable templates for batch creative production.

Quick Start

Ask the skill to run a ComfyUI workflow for your desired output and specify the prompt, seed, model, and input image you want injected.

Frequently Asked Questions about comfyui

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate ComfyUI workflow execution from a text prompt?▼

Automating ComfyUI workflow execution involves injecting parameters like text prompts, seeds, and checkpoints into API-format workflows, then monitoring the queue via REST or WebSocket to retrieve generated images. This Skill handles that orchestration automatically.

Does ComfyUI workflow automation support img2img, inpainting, and video generation?▼

ComfyUI workflow automation supports text-to-image, img2img, inpainting, upscaling, animation, audio, video, and 3D generation scenarios. It verifies model and custom-node dependencies before executing the requested generative media task.

Can I run ComfyUI workflows locally and through Comfy Cloud?▼

You can run ComfyUI workflows locally, through Comfy Desktop, or via Comfy Cloud. The automation handles environment setup, cloud-aware authentication, and download routing to ensure outputs are retrieved safely regardless of the deployment target.

How do I handle missing models and custom nodes in ComfyUI before running a workflow?▼

Handling missing models and custom nodes requires inspecting workflow parameters and checking dependencies before execution. This Skill automates that verification process to ensure all required components are present before queueing the generation task.

What is the best way to swap prompts and LoRAs across reusable ComfyUI templates?▼

Swapping prompts, seeds, checkpoints, LoRAs, and image inputs across reusable templates is managed through parameter injection into API-format workflows. This allows batch creative production without manually reconnecting nodes in the ComfyUI interface.

How do I upload input images and monitor execution for ComfyUI img2img workflows?▼

Uploading input images and monitoring execution for ComfyUI img2img workflows requires handling image uploads and tracking progress via REST and WebSocket connections. This Skill manages both processes to safely download the final generated results.