image-generation

Create Stunning Images from Text with Babes V2.0

25 Apr 2025
Create Stunning Images from Text with Babes V2.0

In the world of digital creativity, harnessing the power of artificial intelligence can significantly enhance your workflow and output. Babes V2.0 offers a robust Cognitive Action that enables developers to generate images directly from textual descriptions. This innovative feature provides a seamless way to transform ideas into visual content, allowing for a high degree of customization in terms of image size, quality, and adherence to the input prompt. Whether you’re a game developer, a digital artist, or someone working on visual content for marketing, this action opens up new avenues for creativity and efficiency.

Imagine needing an illustration for a fantasy novel or a concept art piece for a video game. With Babes V2.0, you can simply describe the scene you envision, and the model will generate an image that brings your words to life. This not only saves time but also reduces the need for extensive graphic design skills. The ability to specify parameters such as image size, quality, and even undesirable elements means you can refine the output to meet your exact needs.

Prerequisites

To get started with Babes V2.0, you will need an API key for the Cognitive Actions service and a general understanding of making API calls. This will allow you to integrate the image generation capabilities into your applications effectively.

Generate Image from Text with Babes 2.0

The primary action offered by Babes V2.0 is the ability to generate images based on detailed text prompts.

Purpose

The "Generate Image from Text" action allows users to create unique images from their descriptions, solving the problem of finding or creating visuals that match specific ideas or themes.

Input Requirements

The input for this action must be structured as a JSON object with the following key properties:

  • prompt: A string that describes the desired image (e.g., a medieval village in Switzerland).
  • width: An integer specifying the image width, selectable from predefined values.
  • height: An integer specifying the image height, also from predefined options.
  • guidanceScale: A number that influences how closely the generated image matches the prompt.
  • negativePrompt: A string to specify elements to avoid in the image.
  • numberOfOutputs: An integer indicating how many images to generate (1 to 4).
  • numberOfInferenceSteps: An integer that determines the quality of the image based on processing steps.
  • scheduler: A string representing the scheduling algorithm used for image generation.
  • seed: An optional integer for random seed generation.

Expected Output

The output will be a URL linking to the generated image, allowing developers to easily access and use the visual content.

Use Cases for this Specific Action

  • Concept Art Creation: Quickly generate visuals for game or movie concepts based on descriptive text.
  • Marketing Material: Produce tailored images for promotional content that resonate with the target audience.
  • Story Illustration: Create illustrations for storytelling, enhancing engagement through visuals that match the narrative.
  • Prototyping: Rapidly prototype visual content for applications or websites without needing extensive graphic design resources.
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 = "690d2df1-2891-4363-8605-a41cb1c4d488" # Action ID for: Generate Image from Text with Babes 2.0

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "width": 512,
  "height": 768,
  "prompt": "(low contrast ), colorfantasystyle sharp details, a medieval village in switzerland, mess jungle in background, ornate, beautiful, atmosphere, vibe, flowers, concept art illustration, greg rutowski, volumetric lighting, sunbeams, particles, colorful clothes, by Jean-Baptiste Monge, Gilles Beloeil, Tyler Edlin, Marek Okon, Pixar, album art, comic style, golden ratio, perfect composition, a masterpiece, trending on artstation, oversaturated, epic realistic, hdr, intricate details, rutkowski, intricate, cinematic, detailed , art by midjourney",
  "scheduler": "EulerAncestralDiscrete",
  "guidanceScale": 7.5,
  "negativePrompt": "disfigured, kitsch, ugly, oversaturated, greain, low-res, Deformed, blurry, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, blurry, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, ugly, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eye, blurry, bad anatomy",
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 30
}

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

Babes V2.0's image generation capabilities provide developers with a powerful tool to create stunning visuals from text prompts effortlessly. By enabling customization and offering a range of parameters, it caters to various creative needs, from concept art to marketing materials. As you integrate this action into your projects, consider how it can streamline your workflow and enhance your creative output. The next step is to experiment with different prompts and settings to fully explore the potential of this innovative technology.

← Back to All Articles