How do I authenticate?

Use COMFYUI_USER and COMFYUI_PASS if your server requires basic auth; otherwise you can omit them.

What if the image is not returned?

Ensure the /run endpoint is accessible and that the workflow produces an image; check the server response for an image field.

Is this compatible with any ComfyUI version?

The skill depends on the presence of the /run endpoint; ensure your ComfyUI version implements it.

Comfyui anfrage

Scanned

@Xtopher86

npx machina-cli add skill @Xtopher86/comfyui-request --openclaw

Files (1)

SKILL.md

1.1 KB

comfyui-request

Purpose

Send a workflow request to a running ComfyUI instance and return the generated image URL or base64 data.

Configuration

COMFYUI_HOST: Host/IP of the ComfyUI server (default 192.168.179.111).
COMFYUI_PORT: Port of the ComfyUI server (default 28188).
COMFYUI_USER: Optional username for basic auth.
COMFYUI_PASS: Optional password for basic auth.

These can be set via environment variables or a .env file in the skill directory.

Usage

{
  "action": "run",
  "workflow": { ... }   // JSON workflow object
}

The skill will POST to http://{host}:{port}/run and return the response JSON.

Example

{
  "action": "run",
  "workflow": {
    "nodes": [ ... ],
    "edges": [ ... ]
  }
}

Notes

The skill expects the ComfyUI server to expose the /run endpoint and return a JSON object containing an image field with a URL or base64 string.

Source

git clone https://clawhub.ai/Xtopher86/comfyui-requestView on GitHub

Overview

Send a workflow to a running ComfyUI instance via POST /run and receive the generated image URL or base64 data. Configure host, port, and optional basic auth through environment variables or a .env file.

How This Skill Works

The skill POSTs to http://{host}:{port}/run with a JSON body containing action and the workflow. It returns a JSON response that includes an image field with a URL or base64 string for immediate use.

When to Use It

Automate image generation from a predefined ComfyUI workflow in a local AI pipeline.
Generate product or asset images on demand from a web app or bot.
In CI or automation scripts to render assets as part of a build.
Reuse workflows by swapping nodes/edges to create variations.
Integrate with other services by retrieving image URLs or base64 data to display or store.

Quick Start

Step 1: Configure COMFYUI_HOST, COMFYUI_PORT and optional COMFYUI_USER/COMFYUI_PASS in a .env or environment.
Step 2: Create a valid workflow JSON and call the skill with action: run and the workflow.
Step 3: Parse response.image (URL or base64) and render or save it.

Best Practices

Validate the workflow JSON before sending to avoid server errors.
Keep COMFYUI_HOST/PORT reachable and secure; use .env for credentials.
Prefer using the image URL when possible to minimize payload size.
Handle both URL and base64 image outputs in your UI.
Set timeouts and robust error handling for failed runs.

Example Use Cases

Basic run: trigger a workflow and display response.image as a preview in a dashboard.
Authenticated run: access a private ComfyUI server using COMFYUI_USER and COMFYUI_PASS.
Frontend integration: a button posts a workflow and renders the returned image URL.
CI asset generation: script generates images during build and saves the image URL.
Workflow variation: reuse the same logic with different workflow nodes/edges to create variants.

Frequently Asked Questions

Add this skill to your agents