image-generation

Create Stunning Images from Text Prompts with Tuiwen

27 Apr 2025
Create Stunning Images from Text Prompts with Tuiwen

In today's digital landscape, the ability to generate high-quality images from textual descriptions is transforming creative workflows across industries. Tuiwen offers developers a powerful Cognitive Action that allows you to generate images based on customizable text prompts. This service simplifies the creative process, enabling quick and deterministic outputs while offering options for randomization. Whether you're building an application for art generation, marketing, or content creation, Tuiwen's image generation capabilities can significantly enhance your projects.

Prerequisites

To get started, you'll need a Tuiwen Cognitive Actions API key and a basic understanding of making API calls.

Generate Image from Prompt

The "Generate Image from Prompt" action is designed to create images based on user-defined textual prompts. This feature is particularly valuable for developers looking to automate visual content creation, allowing for a high degree of customization and control over the output.

Purpose

This action solves the challenge of generating visual representations from textual descriptions, providing a fast and efficient way to create images that meet specific requirements. By adjusting parameters such as image dimensions, guidance scale, and the number of outputs, developers can tailor the generated images to fit various applications.

Input Requirements

The input for this action is structured as a JSON object that includes the following fields:

  • prompt: A string that describes the desired image content (default: "1girl, long hair, blossom").
  • width: The width of the output image in pixels (default: 768, options: 512 to 1024).
  • height: The height of the output image in pixels (default: 768, options: 512 to 1024).
  • guidanceScale: A number that controls the level of guidance during image generation (default: 7.5, range: 1 to 20).
  • numberOfOutputs: An integer indicating how many images to generate (default: 1, range: 1 to 4).
  • numberOfInferenceSteps: An integer specifying the number of denoising steps (default: 50, range: 1 to 500).
  • scheduler: A string to select the scheduler for processing (default: "DPMSolverMultistep").
  • seed: An integer for setting a random seed for deterministic outputs (optional).
  • negativePrompt: A string to specify elements to exclude from the output (optional).

Expected Output

The output will be a URL link to the generated image(s). For example:

["https://assets.cognitiveactions.com/invocations/96198e39-cbf3-434c-9136-f7d383cf33cd/8c229b2b-2c34-4a54-afcb-5d22cacb90be.png"]

Use Cases for this Specific Action

  • Content Creation: Automatically generate images for blog posts, articles, or social media content based on written descriptions.
  • Art Generation: Create unique artwork based on specific themes or concepts, allowing artists to explore new ideas and styles.
  • Marketing Materials: Quickly produce images for promotional campaigns, product showcases, or advertisements tailored to particular audiences.
  • Game Development: Generate assets such as characters or environments based on narrative prompts, enhancing the creative process in game design.
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 = "ffcfc0a1-a471-4a37-b319-484027fbec84" # Action ID for: Generate Image from Prompt

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "seed": 567889,
  "width": 768,
  "height": 768,
  "prompt": "1girl, long hair, blossom",
  "scheduler": "DPMSolverMultistep",
  "guidanceScale": 7.5,
  "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

Tuiwen's "Generate Image from Prompt" action empowers developers to create visually appealing images from textual descriptions effortlessly. By leveraging its customizable parameters, you can generate content tailored to your specific needs, whether for marketing, content creation, or art. Take the next step in your development journey by integrating Tuiwen's capabilities into your projects and unlock new creative possibilities.

← Back to All Articles