skills.rest
humanerd-drew
humanerd-drewOFFICIAL
Explore all skills by this author →
GitHub

comfyui

Generate images, video, and audio via ComfyUI REST and WebSocket APIs.

2|7|Updated Jun 19, 2026
Search Tags:#image generation#audio generation#video generation#generative ai#comfyui
One-click install
npx skills add https://github.com/humanerd-drew/opencode-drewgent --skill comfyui-humanerd-drew
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/humanerd-drew/opencode-drewgent/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/humanerd-drew/opencode-drewgent --skill comfyui-humanerd-drew

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides an interface to ComfyUI, enabling the generation of images, video, and audio content using various workflows and parameters.

Core Features & Use Cases

  • Image Generation: Create images with Stable Diffusion, SDXL, Flux, SD3, etc., using different models and parameters.
  • Video Generation: Produce videos using AnimateDiff, Hunyuan, Wan, AudioCraft, etc., with various parameters and effects.
  • Audio Generation: Create audio content with different generators and settings.
  • Use Case: Imagine you want to create a video of a text-to-video animation with ComfyUI. You can use this Skill to generate the video content based on your input text and desired parameters.

Quick Start

Use the comfyui skill to generate a text-to-video animation with the following parameters: prompt="a fox in a misty forest", model="mm_sd_v15_v2.ckpt", motion_scale=1.0, apply_v2_models_properly=true, output_dir="./videos".

Frequently Asked Questions about comfyui

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

FAQPage Schema
How do I generate images, video, and audio with ComfyUI workflows?▼

To generate images, video, and audio with ComfyUI, you can use this Skill to interface with ComfyUI's REST and WebSocket APIs. It supports various models like Stable Diffusion, SDXL, Flux, AnimateDiff, and AudioCraft to produce content based on your input parameters.

Can I create a text-to-video animation using ComfyUI?▼

Yes, you can create a text-to-video animation using ComfyUI by specifying parameters like prompt, model, and motion scale. For example, use the AnimateDiff or Hunyuan models with your input text to generate the desired video content.

Do I need ComfyUI installed and running to generate images?▼

Yes, you need ComfyUI installed and running to generate images, video, and audio. This Skill acts as an interface to ComfyUI's REST and WebSocket APIs, requiring an active local or remote ComfyUI server to process workflows.

What generative AI models are supported for image and video generation?▼

Supported generative AI models for image generation include Stable Diffusion, SDXL, Flux, and SD3. For video generation, it supports models like AnimateDiff, Hunyuan, and Wan, while audio generation uses various dedicated generators.

How does the ComfyUI API handle audio generation?▼

The ComfyUI API handles audio generation by interfacing with ComfyUI's REST and WebSocket APIs to process audio workflows. You can create audio content by configuring different generators and settings within your ComfyUI setup.

Related Skills

Explore More Design & Creative Skills→
venetanjivenetanji
3

comfyui

Generate images and videos by invoking ComfyUI workflows via REST API.

Community
Advanced
ramonclaudioramonclaudio
4

frames

Extract frames from video files using ffmpeg and ffprobe.

Community
Advanced
89jobrien89jobrien
4

prompt-optimization

Optimize LLM prompts with structured design, few-shot patterns, and chain-of-thought reasoning.

Community
Advanced
inference-shinference-sh
688

ai-content-pipeline

Orchestrate multi-step AI content pipelines for image, video, audio, and text.

Official
Advanced