Generate Stunning Images with the cjwbw/stable-diffusion-v2 Cognitive Actions

22 Apr 2025
Generate Stunning Images with the cjwbw/stable-diffusion-v2 Cognitive Actions

In the realm of artificial intelligence, generating images from textual descriptions has surged in popularity, with numerous applications in creative fields, marketing, and beyond. The cjwbw/stable-diffusion-v2 API provides a powerful toolset for developers looking to harness the capabilities of the Stable Diffusion v2 model. This model leverages advanced diffusion techniques to create high-resolution images based on user-defined text prompts, allowing for extensive customization and flexibility.

Prerequisites

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

  • An API key for the Cognitive Actions platform, which will be required for authentication.
  • Basic familiarity with JSON and HTTP requests, as you'll be constructing payloads to interact with the API.

Authentication typically involves including your API key in the request headers. This ensures that your requests are authorized and can be processed by the server.

Cognitive Actions Overview

Generate Image with Stable Diffusion v2

Description: This action utilizes the Stable Diffusion v2 model to generate images guided by a text prompt. It supports various options for customizing output dimensions and scheduling algorithms, focusing on improved denoising and optimization for V100 GPUs.

Category: Image Generation

Input

The action requires a structured input following the JSON schema outlined below. Here’s an overview of the required and optional fields:

  • seed (integer): Random seed for generating variations. Leave blank for a random seed.
  • width (integer): Width of the output image in pixels (128 to 1024). Default is 768.
  • height (integer): Height of the output image in pixels (128 to 1024). Default is 768.
  • prompt (string): The textual description guiding the image generation. Default is "a photo of an astronaut riding a horse on mars".
  • scheduler (string): Algorithm for scheduling the denoising steps (DDIM, K_EULER, DPMSolverMultistep). Default is K_EULER.
  • initialImage (string, URI): URI of an initial image for generating variations.
  • guidanceScale (number): Scale factor for classifier-free guidance (1 to 20). Default is 7.5.
  • negativePrompt (string): Guides against specific outcomes; ignored if guidance is not used.
  • promptStrength (number): Intensity of the prompt with respect to the initial image (0 to 1). Default is 0.8.
  • numberOfOutputs (integer): Number of images to output (1 to 3). Default is 1.
  • numberOfInferenceSteps (integer): Total denoising steps (1 to 500). Default is 50.

Example Input:

{
  "width": 768,
  "height": 768,
  "prompt": "a photo of an astronaut riding a horse on mars",
  "scheduler": "K_EULER",
  "guidanceScale": 7.5,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 50
}

Output

The action returns a list of URLs pointing to the generated images. Here’s a practical example of a successful output:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/8b513261-0c18-4f62-801d-38b54d58c927/6cfb87e4-415e-4919-9bbe-1956127ef558.png"
]

Conceptual Usage Example (Python)

To invoke this action, you might structure your Python code as follows:

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 = "a9099848-ac73-400d-81d1-d2d18beef1a2"  # Action ID for Generate Image with Stable Diffusion v2

# Construct the input payload based on the action's requirements
payload = {
    "width": 768,
    "height": 768,
    "prompt": "a photo of an astronaut riding a horse on mars",
    "scheduler": "K_EULER",
    "guidanceScale": 7.5,
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "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 code snippet, the action_id corresponds to the "Generate Image with Stable Diffusion v2" action, and the payload is structured according to the required input schema. The endpoint URL and request structure are illustrative.

Conclusion

The cjwbw/stable-diffusion-v2 Cognitive Actions provide developers with a robust framework for generating images based on textual prompts, unlocking new creative possibilities. With customizable options like image dimensions, scheduling algorithms, and guidance scales, you can create unique visual content tailored to your applications. Consider experimenting with different prompts and configurations to see the full potential of image generation in your projects!

← Back to All Articles