Generate Stunning Images with the SD1.5 and Consistency Decoder Action

23 Apr 2025
Generate Stunning Images with the SD1.5 and Consistency Decoder Action

In the ever-evolving world of artificial intelligence, generating compelling images from text prompts has become increasingly accessible. The SD1.5 and Consistency Decoder action from the anotherjesse/sd15-consistency-decoder-vae spec streamlines this process by utilizing a powerful image generation model enhanced by OpenAI's Consistency Decoder. This action allows developers to generate high-quality images while providing customizable parameters to ensure that the output meets specific requirements.

Prerequisites

Before diving into the integration of the Cognitive Actions, ensure you have the following:

  • An API key for accessing the Cognitive Actions platform.
  • Basic understanding of JSON and RESTful API concepts.
  • Familiarity with Python for making API calls is beneficial but not mandatory.

Authentication typically involves including the API key in the request headers, which allows secure access to the action's capabilities.

Cognitive Actions Overview

Generate Image with SD1.5 and Consistency Decoder

Description: This action generates images using the SD1.5 model, enhanced by OpenAI's Consistency Decoder for improved stability and output results. Developers can customize the output by specifying parameters such as image dimensions, guidance scale, and scheduler settings.

Category: image-generation

Input

The input for this action follows the CompositeRequest schema, comprising several fields that allow for extensive customization:

  • seed (integer): Random seed for generating images. Leave blank to use a randomized seed.
    Example: 0
  • width (integer): Width of the output image in pixels, with options ranging from 128 to 1024.
    Example: 512
  • height (integer): Height of the output image in pixels, with options similar to width.
    Example: 512
  • prompt (string): A text prompt used to generate the image, describing the desired output content.
    Example: "a illustration of an bunny on a rainbow"
  • scheduler (string): The algorithm for controlling the sampling process during image generation.
    Example: "DPMSolverMultistep"
  • guidanceScale (number): The level of guidance for classifier-free mechanics during image generation, ranging from 1 to 20.
    Example: 7.5
  • negativePrompt (string): Directives specifying content to exclude from the image output.
    (Optional)
  • numberOfOutputs (integer): The number of images to generate, ranging from 1 to 4.
    Example: 4
  • consistencyDecoder (boolean): Toggle to enable or disable the consistency decoder for stable output results.
    Example: true
  • numberOfInferenceSteps (integer): The number of steps employed in the denoising process during image creation, ranging from 1 to 500.
    Example: 50

Example Input:

{
  "seed": 0,
  "width": 512,
  "height": 512,
  "prompt": "a illustration of an bunny on a rainbow",
  "scheduler": "DPMSolverMultistep",
  "guidanceScale": 7.5,
  "numberOfOutputs": 4,
  "consistencyDecoder": true,
  "numberOfInferenceSteps": 50
}

Output

The action typically returns an array of URLs pointing to the generated images. A successful execution will yield a response similar to the following:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/f788bef7-5d4b-4d1d-a454-d31f8c12707c/f0af1c50-77cc-488d-84a0-ee6b86aaeca2.png",
  "https://assets.cognitiveactions.com/invocations/f788bef7-5d4b-4d1d-a454-d31f8c12707c/bc97c142-53e3-4341-9200-d4973b561fe8.png",
  "https://assets.cognitiveactions.com/invocations/f788bef7-5d4b-4d1d-a454-d31f8c12707c/b15cfcb8-a3ea-40fb-a5c5-2ad608e11b30.png",
  "https://assets.cognitiveactions.com/invocations/f788bef7-5d4b-4d1d-a454-d31f8c12707c/f03e3c85-dc89-4c24-a3cc-33824a026107.png"
]

Conceptual Usage Example (Python)

Here's a conceptual example of how you might call the Generate 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 = "eb3bedbd-b351-4b8d-b089-503bdd06111a" # Action ID for Generate Image with SD1.5 and Consistency Decoder

# Construct the input payload based on the action's requirements
payload = {
    "seed": 0,
    "width": 512,
    "height": 512,
    "prompt": "a illustration of an bunny on a rainbow",
    "scheduler": "DPMSolverMultistep",
    "guidanceScale": 7.5,
    "numberOfOutputs": 4,
    "consistencyDecoder": True,
    "numberOfInferenceSteps": 50
}

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 example, you will replace the COGNITIVE_ACTIONS_API_KEY with your actual API key, and the payload is structured according to the required input for the action. The output will be a list of image URLs that you can then utilize in your application.

Conclusion

The Generate Image with SD1.5 and Consistency Decoder action offers developers a powerful tool to create visually stunning images based on text prompts while providing flexibility through various customizable parameters. By integrating this action into your applications, you can enhance user experience and open up new possibilities for creativity.

Explore further by experimenting with different prompts and parameters to see the diverse outputs you can generate!

← Back to All Articles