text-to-image

Create Stunning Images from Text Prompts with Tensor 2

26 Apr 2025
Create Stunning Images from Text Prompts with Tensor 2

In the world of artificial intelligence, the ability to generate images from text prompts has become a game-changer for developers and creators alike. Tensor 2 offers a powerful Cognitive Action that allows you to transform your ideas into vivid visuals effortlessly. This action streamlines the image creation process, enabling you to produce high-quality images based on simple text descriptions. Whether you're a designer looking to visualize concepts or a developer building an application that requires dynamic image generation, Tensor 2's text-to-image functionality can save you time and enhance creativity.

Imagine being able to generate a unique logo or an artwork simply by typing a few words. The benefits of using this service include speed, flexibility in configuration, and the ability to incorporate safety checks for content, making it ideal for a variety of applications such as marketing, gaming, content creation, and more.

Prerequisites

To get started with Tensor 2's Cognitive Actions, you'll need an API key and a basic understanding of making API calls.

Generate Image from Text Prompt

The "Generate Image from Text Prompt" action utilizes a sophisticated text-to-image generation model to create images based on your specified text. This action is particularly useful for developers who want to automate the creation of visual content without needing extensive design skills.

Input Requirements

To use this action, you need to provide the following inputs:

  • Prompt: A descriptive text that outlines the desired image (e.g., "a logo of a car").
  • Width and Height: Specify dimensions for the output image, ensuring they do not exceed 1024x768 due to memory constraints.
  • Scheduler: Choose from various image generation schedulers to determine how the image is processed.
  • Guidance Scale: Affects how closely the output adheres to the prompt; higher values yield more accurate representations.
  • Safety Checker: Optionally enable this feature to detect potentially unsafe content in the generated image.
  • Negative Prompt: Specify elements to exclude from the image.
  • Number of Outputs: Define how many images you want the action to generate (up to 4).
  • Inference Steps: Control the number of denoising steps to enhance image quality.

Example Input:

{
  "width": 768,
  "height": 768,
  "prompt": "a logo of a car",
  "scheduler": "K_EULER_ANCESTRAL",
  "guidanceScale": 7.5,
  "safetyChecker": "no",
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 50
}

Expected Output

The output will be a URL link to the generated image, which you can then use in your applications or share with others.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/dfb44a24-466a-4349-9170-f654af0de100/b08a92d6-1c0c-46e1-b5aa-088547a8d57d.png"
]

Use Cases for this Action:

  • Marketing: Create promotional materials or social media graphics quickly.
  • Gaming: Generate in-game assets or character designs based on textual descriptions.
  • Content Creation: Produce unique illustrations for articles, blogs, or presentations.
  • Prototyping: Visualize product concepts or logo designs without needing a graphic designer.
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 = "3ed5cd98-e74b-4eb8-a438-42e196bd913e" # Action ID for: Generate Image from Text Prompt

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "width": 768,
  "height": 768,
  "prompt": "a logo of a car",
  "scheduler": "K_EULER_ANCESTRAL",
  "guidanceScale": 7.5,
  "safetyChecker": "no",
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 50
}

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("------------------------------------------------")

Conclusion

Tensor 2's "Generate Image from Text Prompt" action empowers developers to bring their ideas to life with just a few words. The flexibility and ease of use make it an invaluable tool for various industries, from creative arts to technology. By leveraging this Cognitive Action, you can enhance your projects, streamline workflows, and ultimately create stunning visual content that resonates with your audience. Start exploring the possibilities today and transform your text prompts into captivating images!

← Back to All Articles