Seamlessly Execute ComfyUI Workflows with Cognitive Actions

24 Apr 2025
Seamlessly Execute ComfyUI Workflows with Cognitive Actions

In the world of AI-driven applications, leveraging powerful workflows can significantly enhance your project's capabilities. The fofr/any-comfyui-workflow provides developers with a robust set of Cognitive Actions designed to execute specified ComfyUI workflows using the Replicate API. These pre-built actions allow for the customization of inputs such as images or videos, with support for various output formats and qualities. In this article, we will explore how to integrate the Execute ComfyUI Workflow action into your applications.

Prerequisites

Before diving into the integration, make sure you have the following:

  • An API key for accessing the Cognitive Actions platform.
  • Basic familiarity with JSON and RESTful APIs.
  • A setup that allows you to make HTTP requests (e.g., Python environment with the requests library).

Authentication typically involves passing your API key in the request headers, which will allow you to execute the actions securely.

Cognitive Actions Overview

Execute ComfyUI Workflow

The Execute ComfyUI Workflow action allows you to run a specified ComfyUI workflow utilizing the Replicate API. This action supports JSON-based workflows, enabling flexibility in manipulating inputs like images or videos, while offering different output formats and quality settings.

  • Category: Workflow Orchestration

Input

The input for this action is structured as a JSON object with several fields. Here’s a breakdown of the required and optional fields based on the schema:

  • inputFile (string, required): The URI of an input file (image, video, tar, or zip). You can use URLs for automatic downloads. More guidance can be found here.
  • outputFormat (string, optional): Specifies the format of the output images (options: 'webp', 'jpg', 'png'). Default is 'webp'.
  • workflowJson (string, required): The ComfyUI workflow in JSON format or as a URL. Ensure to use the API version of your workflow, obtainable via 'Save (API format)' in ComfyUI. Detailed instructions are available here.
  • outputQuality (integer, optional): Defines the quality of the output images on a scale from 0 to 100. Default is 95.
  • randomizeSeeds (boolean, optional): Automatically randomizes seeds. Default is true.
  • forceResetCache (boolean, optional): Resets the ComfyUI cache before executing the workflow. Default is false.
  • returnTempFiles (boolean, optional): If true, returns temporary files useful for debugging. Default is false.

Here’s an example input JSON payload:

{
  "outputFormat": "webp",
  "workflowJson": "{\n  \"3\": {...}\n}",
  "outputQuality": 80,
  "randomizeSeeds": true,
  "forceResetCache": false,
  "returnTempFiles": false
}

Output

The output of this action typically returns a URL pointing to the generated image or video. For example:

[
  "https://assets.cognitiveactions.com/invocations/05e304eb-8c1a-4e27-bf29-44275a933440/3c4af781-b321-46d5-a998-461fa574de36.webp"
]

The output can vary based on the workflow's specifications and the inputs provided.

Conceptual Usage Example (Python)

The following code snippet demonstrates how a developer might call the Execute ComfyUI Workflow action using Python:

import requests
import json

# Replace with your Cognitive Actions API key and endpoint
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute"  # Hypothetical endpoint

action_id = "a8974a95-d5a4-4e33-8cd7-93e54fe42ca6"  # Action ID for Execute ComfyUI Workflow

# Construct the input payload based on the action's requirements
payload = {
    "outputFormat": "webp",
    "workflowJson": "{\n  \"3\": {...}\n}",
    "outputQuality": 80,
    "randomizeSeeds": True,
    "forceResetCache": False,
    "returnTempFiles": False
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json"
}

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json={"action_id": action_id, "inputs": payload}  # Hypothetical structure
    )
    response.raise_for_status()  # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully:")
    print(json.dumps(result, indent=2))

except requests.exceptions.RequestException as e:
    print(f"Error executing action {action_id}: {e}")
    if e.response is not None:
        print(f"Response status: {e.response.status_code}")
        try:
            print(f"Response body: {e.response.json()}")
        except json.JSONDecodeError:
            print(f"Response body: {e.response.text}")

In this snippet, you’ll notice how the action ID and input payload are structured. The endpoint URL and request structure are illustrative and should be adapted to match your actual API setup.

Conclusion

The Execute ComfyUI Workflow action empowers developers to integrate sophisticated workflows into their applications with ease. By utilizing these Cognitive Actions, you can automate image and video processing, harnessing the power of customizable workflows. As a next step, consider experimenting with different input configurations and output formats to fully explore the capabilities of the ComfyUI framework. Happy coding!

← Back to All Articles