Text to Image API Documentation

Text Validation Endpoint

• Method: POST
• Path: https://api.kadal.ai/text-to-image/api/v1/text_validation
• Summary: Validates input text for suitability in image generation.

Description

This endpoint verifies that the provided text is well-formed and interpretable, ensuring it can be processed effectively to generate a corresponding image.

Request

• Content-Type: multipart/form-data

Payload

Parameter	Description	Data Type	Is Optional
input_text	Text corresponding to which an image needs to be generated	String	No

Response

Success (200 OK)

{
  "status_code": 200,
  "message": "SUCCESS::Text Validation generated successfully",
  "input_text": "Your input text result will appear here"
}

Usage

import requests

url = "https://api.kadal.ai/text-to-image/api/v1/text_validation"
token = "your_token_here"

headers = {
    "accept": "application/json",
    "Authorization": f"Bearer {token}",
    "Content-Type": "application/x-www-form-urlencoded",
}

data = {
    "input_text": """A paper craft art depicting a girl giving her cat a gentle hug. Both sit amidst potted plants, with the cat purring contentedly while the girl smiles. The scene is adorned with handcrafted paper flowers and leaves."""
}

response = requests.post(url, headers=headers, data=data)

Text to Image Generation Endpoint

• Method: POST
• Path: https://api.kadal.ai/text-to-image/api/v1/text_to_image
• Summary: Generates images from text with configurable count and aspect ratio.

Description

This endpoint generates images from input text using a selected AI model, with options to set the number of images and aspect ratio.

Request

• Content-Type: multipart/form-data

Payload

Parameter	Description	Data Type	Constraints / Allowed Values	Optional
user_model_selection	AI model used for generation	String	Must be one of: dall-e-3	No
input_text	Input text prompt	String	Non-empty; max length: 300 chars	No
number_of_images	Number of images to generate	String	Range: 1–3	No
aspect_ratio	Aspect Ratio of images	String	Must be one of: 1:1, 16:9, 9:16	No

Response:

{
  "status_code": 200,
  "message": "SUCCESS::Text to Image generated successfully",
  "images_created": {
    "image_url_1": "Your image_url will appear here",
    "image_url_2": "Your image_url will appear here",
    "image_url_3": "Your image_url will appear here"
  }
}

Usage

import requests

url = "https://api.kadal.ai/text-to-image/api/v1/text_to_image"
token = "your_token_here"

headers = {
    "accept": "application/json",
    "Authorization": f"Bearer {token}",
    "Content-Type": "application/x-www-form-urlencoded",
}

data = {
    "user_model_selection": "dall-e-3",
    "input_text": """A paper craft art depicting a girl giving her cat a gentle hug. Both sit amidst potted plants, with the cat purring contentedly while the girl smiles. The scene is adorned with handcrafted paper flowers and leaves.""",
    "number_of_images": "3",
    "aspect_ratio": "1:1",
}

response = requests.post(url, headers=headers, data=data)

Text to Image Generation Endpoint V2

• Method: POST
• Path: https://api.kadal.ai/text-to-image/api/v1/text_to_image_v2
• Summary: Generates images from text with configurable count and aspect ratio.

Description

This endpoint generates images from input text using a selected AI model, with options to set the number of images and aspect ratio.

Request

• Content-Type: application/json

Payload

Parameter	Description	Data Type	Constraints / Allowed Values	Optional
provider	AI Provider used for generation	String	Must be one of: azure, vertexai	No
model_name	Model used for generation	String	model name of the model	No
input_text	Prompt	String	Prompt of the Image	No
number_of_images	Number of Images	Integer	Range: 1-4	No
aspect_ratio	Aspect Ratio of images	String	Must be one of: AUTO, SQUARE, LANDSCAPE, PORTRAIT	No
base64_images	Base64 of the images	Bool	Must be one of: true, false	Yes (default false)

Response:

Response Json

{
  "status_code": 200,
  "message": "Images generated successfully",
  "images_created": [
    {
      "Image_url": "https://learningmate.co/assets/aigenerated/tmp/{tenant_id}/{user_id}/xxxxx.png"
    }
  ],
  "text_generated": "Here's a car from the future! "
}

Usage

Example code for curl:

cURL

curl -X 'POST' \
  'https://api.kadal.ai/text-to-image/api/v1/text_to_image_v2' \
  -H 'accept: application/json' \
  -H 'api-key: LM-xxxxx' \
  -H 'Content-Type: application/json' \
  -d '{
  "provider": "vertexai",
  "model_name": "gemini-2.5-flash-image",
  "input_text": "a car from future",
  "number_of_images": 1,
  "aspect_ratio": "AUTO",
  "base64_images": false
}'

Example code for Python:

Python

import requests
import json

lm_key = "LM-xxxxxxxx" # LM key from you profile

# Define the endpoint URL
url = 'https://api.kadal.ai/text-to-image/api/v1/text_to_image_v2'

# Set up the headers
headers = {
    'accept': 'application/json',
    'api-key': lm_key,
    'Content-Type': 'application/json'
}

# Define the payload (the data you are sending)
data = {
    "provider": "vertexai", # Provider 
    "model_name": "gemini-2.5-flash-image", # Model name 
    "input_text": "a car from future", # Prompt
    "number_of_images": 1,  # Number of Image (1-4)
    "aspect_ratio": "AUTO", # Ratio: AUTO, SQUARE, LANDSCAPE, PORTRAIT 
    "base64_images": False # Base_64 of the Images 
}

try:
    # Make the POST request
    response = requests.post(url, headers=headers, json=data)

    # Check if the request was successful
    response.raise_for_status()

    # Parse and print the JSON response
    result = response.json()
    print(json.dumps(result, indent=4))

except requests.exceptions.HTTPError as http_err:
    print(f"HTTP error occurred: {http_err}")
except Exception as err:
    print(f"An error occurred: {err}")