comfyui

Name: comfyui
Availability: InStock
Author: whichguy

Generate images, videos, and audio using ComfyUI workflows.

1|Updated Jun 23, 2026

Search Tags:#image generation #AI #audio generation #video generation #ComfyUI

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill solves the problem of generating images, video, and audio using ComfyUI, a powerful tool for creative AI applications.

Core Features & Use Cases

Image Generation: Create custom images using Stable Diffusion, SDXL, Flux, SD3, and other models.
Video Generation: Generate video content using AnimateDiff, Hunyuan, Wan, AudioCraft, and more.
Audio Generation: Produce audio content with various AI models.
Use Case: A designer wants to create a promotional video showcasing their products. They can use this Skill to generate video clips with specific prompts and styles.

Quick Start

To generate an image, run the following command: run_workflow.py --workflow sdxl_txt2img.json --args '{"prompt": "a beautiful cityscape at dusk", "seed": 12345}'

Frequently Asked Questions about comfyui

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

FAQPage Schema

How do I generate images using Stable Diffusion and SDXL models?▼

Generate images with Stable Diffusion and SDXL by executing a workflow script with a JSON configuration, passing your text prompt and a specific seed number to produce the custom visual output.

Can I create AI video content using AnimateDiff and Hunyuan models?▼

Create AI video content using AnimateDiff and Hunyuan models through supported video generation workflows, allowing you to generate dynamic video clips from specific text prompts and styles.

What is the best way to produce AI audio with various generation models?▼

Produce AI audio using integrated generation workflows, utilizing models like AudioCraft to synthesize custom audio content directly from your descriptive text prompts.

Does ComfyUI support Flux and SD3 for custom creative workflows?▼

ComfyUI supports Flux and SD3 for custom creative workflows, integrating these models to allow flexible generation of images, videos, and audio across diverse creative applications.

How do I start a text-to-image workflow with a specific prompt and seed?▼

Start a text-to-image workflow by executing the run_workflow.py script with your desired workflow JSON file, passing a structured arguments string containing your prompt and seed value.