skills.rest
cabezno
cabeznoCOMMUNITY
Explore all skills by this author →
GitHub

comfyui

Execute ComfyUI API-format workflows with parameter injection for image, video, and audio generation.

Updated May 15, 2026
Search Tags:#workflow automation#image-generation#model management#video-generation#stable-diffusion#comfyui#rest-websocket
One-click install
npx skills add https://github.com/cabezno/bmb-encover-agent --skill comfyui-cabezno
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/cabezno/bmb-encover-agent/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/cabezno/bmb-encover-agent --skill comfyui-cabezno

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the friction of installing, configuring, and repeatedly running ComfyUI image/video workflows by turning them into reliable, parameterized executions with automatic dependency checks.

Core Features & Use Cases

  • Lifecycle management: installs, launches, verifies, and health-checks ComfyUI using the official comfy-cli (local or Comfy Cloud flow).
  • Workflow execution with parameter injection: runs API-format workflow JSON by injecting user-specified values (including seeds, prompts, dimensions, and img2img/inpaint inputs).
  • Dependency discovery and remediation: inspects a workflow to detect missing custom nodes, models, and embeddings, then suggests concrete comfy-cli/Manager actions.
  • Real-time monitoring and reliable output download: supports WebSocket progress monitoring and streams result files to a safe output directory.

Quick Start

Generate an SDXL image by asking the AI: "Run the SDXL text-to-image workflow from workflows/sdxl_txt2img.json with prompt 'majestic eagle in flight', seed 12345, and steps 35, saving outputs to ./outputs."

Frequently Asked Questions about comfyui

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

FAQPage Schema
How do I run ComfyUI workflows with parameter injection for image generation?▼

ComfyUI workflow execution runs API-format JSON by injecting user-specified values like seeds, prompts, and dimensions to generate images, video, and audio. It supports text-to-image, img2img, inpainting, and upscaling workflows seamlessly.

Can I use ComfyUI workflows for video generation and animation?▼

Yes, ComfyUI workflows support video generation and animation alongside image and audio creation. Workflow execution handles animation and video workflows with real-time WebSocket progress monitoring and reliable output downloads.

What should I do if my ComfyUI workflow is missing custom nodes or models?▼

ComfyUI dependency discovery inspects workflows to detect missing custom nodes, models, and embeddings, then suggests concrete comfy-cli and Manager actions for remediation. This ensures your workflow execution environment is fully prepared.

Does this approach support both local and Comfy Cloud environments?▼

ComfyUI lifecycle management installs, launches, verifies, and health-checks using the official comfy-cli for both local and Comfy Cloud scenarios. It provides consistent workflow execution across different deployment environments.

How does real-time monitoring work during Stable Diffusion workflow execution?▼

Real-time monitoring during Stable Diffusion workflow execution uses WebSocket connections to stream progress updates. Result files are automatically downloaded to a path-traversal-safe output directory upon completion.

What is needed to automate img2img and inpainting workflows with ComfyUI?▼

Automating img2img and inpainting workflows requires API-format workflow JSON, input images, and parameter values. The system handles dependency checking, parameter injection, and streamed output downloads automatically.

Related Skills

Explore More Design & Creative Skills→
ZardLi1115ZardLi1115
4

comfyui

Execute ComfyUI API-format workflows with parameter injection for image, video, and audio generation.

Community
Advanced
pkoka888pkoka888
1

image-enhancer

Upscale image resolution, sharpen details, and reduce compression artifacts.

Community
Intermediate
partme-aipartme-ai
610

stable-diffusion

Guide Stable Diffusion model selection, prompt engineering, and parameter configuration for image generation.

Official
Intermediate
hungthinh04hungthinh04

comfyui

Automate ComfyUI image, video, and audio workflows with parameter injection and output capture.

Community
Advanced