skills.rest
JamesFincher
JamesFincherCOMMUNITY
Explore all skills by this author →
GitHub

comfyui

Executes ComfyUI API-format workflows to generate images, video, and audio.

Updated May 4, 2026
Search Tags:#image generation#workflow execution#text-to-image#comfyui#inpainting#cloud gpu
One-click install
npx skills add https://github.com/JamesFincher/gengar --skill comfyui-jamesfincher
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/JamesFincher/gengar/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/JamesFincher/gengar --skill comfyui-jamesfincher

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

ComfyUI image and video generation is powerful but setup, dependency management, and parameter tweaking are difficult to do reliably without expert knowledge.

Core Features & Use Cases

  • Workflow execution with parameter injection: Run API-format workflow JSON while injecting prompts, seeds, steps, and other controllable fields, including img2img and inpainting by uploading inputs first.
  • Dependency discovery and auto-remediation: Detect missing custom nodes, checkpoints, embeddings, and required model folders, then suggest or help install the exact fixes.
  • Local vs Cloud execution support: Seamlessly route requests for ComfyUI local servers and Comfy Cloud (with correct endpoint prefixes and API-key handling) and download outputs safely.

Quick Start

Ask the agent: "Generate a text-to-image using the workflow sdxl_txt2img.json with prompt 'majestic eagle in flight', seed 12345, steps 35, and save results 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 a ComfyUI workflow with specific parameters like seed and steps?▼

You can run ComfyUI workflows by providing an API-format JSON file alongside your desired prompt, seed, and step count. The execution engine injects these parameters deterministically into the sampler pipeline without overwriting existing link fields, then streams the generated output for download.

What is the best way to handle missing custom nodes and model dependencies in ComfyUI?▼

Handling missing ComfyUI dependencies uses built-in discovery and auto-remediation to detect absent custom nodes, checkpoints, and embeddings. It then suggests or helps install the exact required fixes, ensuring your workflow execution pipeline runs without interruption.

Does this support running AnimateDiff and video generation workflows on Comfy Cloud?▼

Yes, AnimateDiff, Wan, and other video sampler pipelines are fully supported on Comfy Cloud. The execution engine seamlessly routes REST and WebSocket requests to cloud endpoints with correct API-key handling, downloading streamed video outputs safely.

Can I upload my own images for inpainting and img2img generation?▼

Yes, you can upload your own images for inpainting and img2img generation. The workflow execution supports optional uploaded inputs, allowing you to process custom source images before injecting prompts and applying modifications through the sampler pipeline.

Why does my ComfyUI workflow fail when I try to overwrite link fields?▼

ComfyUI workflows fail when attempting to overwrite link fields because parameter injection intentionally refuses to modify them. This constraint preserves the structural integrity of your API-format workflow JSON while only updating controllable fields like prompts and seeds.

Related Skills

Explore More Design & Creative Skills→
RazonIn4KRazonIn4K
2

gray-swan-ipi-wave-2-executor

Execute Indirect Prompt Injection payloads and collect evidence for Gray Swan AI Arena Wave 2.

Community
Advanced
OpenLoafOpenLoaf
94

media-ops-skill

Process local media files and download public videos for editing.

Official
Intermediate
HouseGarofaloHouseGarofalo
3

browserless

Automate headless Chrome browser tasks via REST API and WebSocket.

Official
Intermediate
hungthinh04hungthinh04

comfyui

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

Community
Advanced