image-generation

Unleash Your Creativity with Kandinsky 2.2 Image Generation

26 Apr 2025
Unleash Your Creativity with Kandinsky 2.2 Image Generation

The Kandinsky 2.2 model offers developers an innovative way to generate and transform images using advanced AI techniques. With its powerful capabilities, including Text2Img, Img2Img, and inpainting functionalities, Kandinsky 2.2 simplifies the process of creating high-quality images tailored to your specific needs. Whether you're looking to create stunning visuals for marketing materials, enhance existing images, or explore artistic concepts, this model provides the tools to achieve exceptional results.

Imagine having the ability to create unique artwork just by describing it in words or enhancing your photos seamlessly. With customizable options such as prompt guidance, output dimensions, and control over inference steps, Kandinsky 2.2 caters to a variety of use cases. From graphic designers to content creators and game developers, anyone can leverage these cognitive actions to streamline their creative workflow and elevate their projects.

Prerequisites

Before you dive into using the Kandinsky 2.2 model, ensure you have a Cognitive Actions API key and a basic understanding of making API calls. This will allow you to access the powerful features of the model effectively.

Generate and Transform Images with Kandinsky Model

The primary action of the Kandinsky 2.2 model is to generate and transform images, enabling users to explore their creativity without limits. This action serves a critical purpose by allowing developers to harness advanced AI for image creation and manipulation.

Purpose

This action solves the challenge of creating compelling images by utilizing a combination of text prompts and existing images. It allows for the generation of new visuals or the modification of existing ones, making it a versatile tool for various applications.

Input Requirements

To use this action, you need to provide several inputs:

  • Prompt: A textual description guiding the content of the output image.
  • Negative Prompt: Elements you want to exclude from the output.
  • Image: The URI of an input image for Img2Img and inpainting modes.
  • Mask: A URI for the mask image used in inpainting mode.
  • Width & Height: Dimensions for the output image, with a maximum of 2048 pixels.
  • Seed: An integer for random number generation, ensuring consistent output.
  • Number of Outputs: How many images to generate (up to 4).
  • Number of Inference Steps: Controls the quality of the output through denoising steps.

Example Input:

{
  "seed": 4697,
  "width": 1024,
  "height": 1024,
  "prompt": "A moss covered astronaut with a black background",
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 75,
  "numberOfInferenceStepsPrior": 25
}

Expected Output

The action will return high-quality image outputs based on the provided inputs, allowing for stunning and creative results. An example output may look like this:

  • Generated Image
import requests
import json

# Replace with your actual Cognitive Actions API key and endpoint
# Ensure your environment securely handles the API key
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
# This endpoint URL is hypothetical and should be documented for users
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute"

action_id = "c7cd1d49-09a6-4edc-b8ed-bb491f467fb1" # Action ID for: Generate and Transform Images with Kandinsky Model

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "seed": 4697,
  "width": 1024,
  "height": 1024,
  "prompt": "A moss covered astronaut with a black background",
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 75,
  "numberOfInferenceStepsPrior": 25
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json",
    # Add any other required headers for the Cognitive Actions API
}

# Prepare the request body for the hypothetical execution endpoint
request_body = {
    "action_id": action_id,
    "inputs": payload
}

print(f"--- Calling Cognitive Action: {action.name or action_id} ---")
print(f"Endpoint: {COGNITIVE_ACTIONS_EXECUTE_URL}")
print(f"Action ID: {action_id}")
print("Payload being sent:")
print(json.dumps(request_body, indent=2))
print("------------------------------------------------")

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json=request_body
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully. Result:")
    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 (non-JSON): {e.response.text}")
    print("------------------------------------------------")

Use Cases for this Specific Action

  • Art Creation: Artists can generate unique pieces by simply describing their vision in words.
  • Marketing Materials: Marketers can quickly create visuals that align with their campaigns, enhancing engagement.
  • Game Design: Developers can create assets for games, from characters to environments, all tailored to their specifications.
  • Content Enhancement: Photographers can enhance existing images or create variations for social media and portfolios.

Conclusion

Kandinsky 2.2 opens a world of possibilities for developers looking to integrate creative image generation into their projects. With its diverse functionalities and customization options, you can streamline your creative process and produce stunning visuals that stand out. Whether you're generating new artwork or transforming existing images, Kandinsky 2.2 is a powerful ally in your creative toolkit.

Ready to explore the full potential of image generation? Start integrating Kandinsky 2.2 into your applications and watch your creative ideas come to life!

← Back to All Articles