comfyui-api

Submit generation workflows and monitor queues on ComfyUI hosts.

Updated May 7, 2026
One-click install
npx skills add https://github.com/MOODMNKY-LLC/mnky-atlas --skill comfyui-api-moodmnky-llc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui-api
Source: https://github.com/MOODMNKY-LLC/mnky-atlas/tree/main/skills/comfyui-api
Command: npx skills add https://github.com/MOODMNKY-LLC/mnky-atlas --skill comfyui-api-moodmnky-llc

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill eliminates the manual overhead of managing the MNKY ComfyUI creative generation stack, removing guesswork from API interactions, workflow debugging, and handoffs between 2D image generation and 3D mesh/scene production tools.

Core Features & Use Cases

  • Full Stack API Control: Interact with local PREP and remote GEN ComfyUI endpoints to check system stats, manage queues, inspect node schemas, and submit generation workflows.
  • Reproducible Workflow Management: Submit and replay generation jobs with explicit workflow JSON, seeds, and node names for consistent, repeatable results.
  • Cross-Tool 3D Handoff: Seamlessly transfer 3D assets between ComfyUI, Hunyuan3D, and Blender via BlenderMCP for end-to-end creative production pipelines.

Quick Start

Use the comfyui-api skill to submit the provided image generation workflow to the remote GEN ComfyUI host and monitor its progress until the job finishes.

Frequently Asked Questions about comfyui-api

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

FAQPage Schema
How do I automate ComfyUI workflow submission and queue monitoring via API?

Automating ComfyUI workflow submission involves sending explicit workflow JSON with seeds and node names to local PREP or remote GEN hosts, then polling system stats to monitor queue progress until the generation job finishes.

Can I transfer 3D models generated in ComfyUI directly to Blender?

Yes, you can transfer 3D assets between ComfyUI, Hunyuan3D, and Blender using BlenderMCP for cross-tool handoffs, enabling an end-to-end creative production pipeline from image generation to 3D mesh scene assembly.

How do I inspect node schemas in a remote ComfyUI generation stack?

Inspecting node schemas in a remote ComfyUI generation stack requires probing the API endpoints with read-only guardrails to query available node definitions and parameters before explicitly parameterizing your reproducible generation jobs.

What is the best way to ensure reproducible image generation results in ComfyUI?

Achieving reproducible image generation results in ComfyUI requires submitting jobs with explicit workflow JSON, fixed seeds, and defined node names, ensuring that generation parameters remain consistent across replays on the accelerator hosts.

Does the comfyui-api skill support managing both local and remote ComfyUI hosts?

Yes, the comfyui-api skill manages interactions across local PREP and remote GEN ComfyUI accelerator hosts, allowing users to check system stats, manage queues, inspect schemas, and submit workflows seamlessly between environments.

Why do my ComfyUI API generation jobs fail when submitted without explicit parameters?

ComfyUI API generation jobs fail without explicit parameters because the stack requires explicit workflow JSON parameterization and adherence to read-only probing guardrails to ensure reproducible generation jobs instead of relying on default states.