Generate Stunning Images with the vetkastar/comfy-flux Cognitive Actions

24 Apr 2025
Generate Stunning Images with the vetkastar/comfy-flux Cognitive Actions

The vetkastar/comfy-flux spec is designed for developers looking to harness the power of AI-driven image generation. With the Generate Flux-Based Image action, users can create high-quality images using advanced models and techniques from the Comfy framework. This action allows for customization in output format and quality while leveraging sophisticated guidance and sampling methods. In this article, we'll explore how to integrate this action into your applications, providing clear examples and conceptual usage.

Prerequisites

To get started with the Cognitive Actions, you'll need:

  • An API key for the Cognitive Actions platform to authenticate your requests. This key is typically passed in the headers of your API requests.
  • A basic understanding of JSON for crafting input payloads.

Cognitive Actions Overview

Generate Flux-Based Image

The Generate Flux-Based Image action allows developers to generate images by utilizing the Flux model in Comfy. It incorporates LoRA, ControlNet, and checkpoint models to create stunning visuals based on specified workflows.

Input:

The action requires a structured input payload defined by the following schema:

  • loraUrls (string, optional): A list of URLs for LoRA models, formatted as one URL per line.
  • inputFile (string, required): A URI pointing to an input file (image, tar, or zip).
  • anyModelUrls (string, optional): Additional model URLs for download, formatted similarly.
  • outputFormat (string, optional): Specifies the output image format. Supported values are webp, jpg, and png (default: webp).
  • workflowJson (string, required): JSON defining the ComfyUI workflow.
  • outputQuality (integer, optional): Quality of the output image (0-100), default is 95.
  • checkpointUrls (string, optional): URLs for checkpoint models.
  • controlnetUrls (string, optional): URLs for ControlNet models.
  • randomizeSeeds (boolean, optional): If true, randomizes the seeds (default: true).
  • forceResetCache (boolean, optional): Resets the ComfyUI cache if true (default: false).
  • returnTempFiles (boolean, optional): Returns temporary files for debugging if true (default: false).

Example Input:

{
  "loraUrls": "",
  "outputFormat": "png",
  "workflowJson": "{\n  \"6\": {\n    \"inputs\": {\n      \"text\": \"flowers with magic waves and circles\",\n      \"clip\": [\n        \"11\",\n        0\n      ]\n    },\n    \"class_type\": \"CLIPTextEncode\",\n    \"_meta\": {\n      \"title\": \"CLIP Text Encode (Positive Prompt)\"\n    }\n  },\n  ...\n}",
  "outputQuality": 80,
  "randomizeSeeds": true,
  "forceResetCache": false,
  "returnTempFiles": false
}

Output:

The action typically returns a URL pointing to the generated image. For example:

[
  "https://assets.cognitiveactions.com/invocations/da2a47cb-120c-4a00-89bd-8e9b66bb6ec7/519a282f-02b5-4fdd-8b39-7c9c24055f57.png"
]

Conceptual Usage Example (Python):

Here’s how you might call the Generate Flux-Based Image 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 = "43b1af01-334d-42e9-978f-114373d598ae" # Action ID for Generate Flux-Based Image

# Construct the input payload based on the action's requirements
payload = {
    "loraUrls": "",
    "outputFormat": "png",
    "workflowJson": "{\n  \"6\": {\n    \"inputs\": {\n      \"text\": \"flowers with magic waves and circles\",\n      \"clip\": [\n        \"11\",\n        0\n      ]\n    },\n    \"class_type\": \"CLIPTextEncode\",\n    \"_meta\": {\n      \"title\": \"CLIP Text Encode (Positive Prompt)\"\n    }\n  },\n  ...\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 code snippet, replace the placeholder API key and endpoint URL with your actual credentials. The input payload is structured as required by the action, and you will receive the generated image URL upon successful execution.

Conclusion

The Generate Flux-Based Image action within the vetkastar/comfy-flux spec empowers developers to create high-quality images using advanced AI techniques. By integrating this action into your applications, you can leverage the latest in image generation technology, enhancing user experiences with stunning visuals. Start experimenting with your workflows today and explore the endless creative possibilities!

← Back to All Articles