comfyui

Execute generative AI workflows via ComfyUI REST and WebSocket APIs.

Updated Jun 25, 2026

Search Tags:#automation #workflow #generative-ai #video-generation #stable-diffusion #comfyui

Ready to run

npx skills add https://github.com/Rheasilvia/hermes-desktop --skill comfyui-rheasilvia

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill bridges the gap between the ComfyUI desktop interface and automated agentic workflows, allowing you to programmatically execute complex generative AI pipelines for images, video, and audio.

Core Features & Use Cases

Workflow Execution: Run complex diffusion pipelines (SDXL, Flux, Wan Video) via REST/WebSocket APIs.
Dependency Management: Automatically detect and install missing custom nodes and models required for specific workflows.
Use Case: You can chain a text-to-image generation step with an upscaling and video-animation pass, ensuring all required custom nodes are installed and the GPU hardware is correctly configured before execution.

Quick Start

Ask the agent to run the workflow file named flux_dev_txt2img.json with a specific prompt and save the output to your local directory.

Frequently Asked Questions about comfyui

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

FAQPage Schema

How do I automate Stable Diffusion workflows without using the ComfyUI desktop interface?▼

You can automate Stable Diffusion workflows by using this skill to execute generative AI pipelines via ComfyUI REST and WebSocket APIs. It bridges the desktop interface and automated agentic workflows for programmatic media generation.

Can I run text-to-video and image-to-image generation pipelines programmatically?▼

Yes, you can run text-to-video and image-to-image generation pipelines programmatically. The skill executes complex diffusion pipelines like SDXL, Flux, and Wan Video, supporting advanced latent space manipulation for media tasks.

Does executing generative AI workflows require specific GPU hardware verification?▼

Yes, executing generative AI workflows requires GPU hardware verification. The skill manages the lifecycle of local or cloud-hosted ComfyUI instances, ensuring the GPU hardware is correctly configured before running diffusion pipelines.

How do I handle missing custom nodes and models when running ComfyUI workflows?▼

To handle missing custom nodes and models, the skill provides automatic dependency management. It detects and installs required custom nodes and models for specific workflows before executing the generation pipeline.

What is the best way to chain a text-to-image step with an upscaling and video-animation pass?▼

The best way to chain generation steps is using this skill to automate the pipeline. It executes the text-to-image generation, then handles the upscaling and video-animation passes while ensuring all required nodes are installed.

Why does my automated ComfyUI execution fail when starting cloud-hosted instances?▼

Automated ComfyUI execution may fail if model dependencies are unresolved or GPU hardware verification fails. The skill manages instance lifecycles and automatically resolves model dependencies to prevent execution errors.