Function Documentation: OpenAI → Generate an image (Simple)

OpenAI Vision API

Overview

This function generates an image using the OpenAI API based on a text prompt, with options for size and model. It is designed to take user input, validate it, and return an image URL if the request is successful.

Inputs

1. openai_api_key (registry | text)

   • Purpose: API key required to authenticate with OpenAI's image generation endpoint.
   • Example: "sk-...your-key-here"

2. prompt (text)

   • Purpose: The text description for the image to generate.
   • Example: "A futuristic city with flying cars"

3. img_size (enum)

   • Purpose: The size of the generated image.
   • Options:
     • "1024x1024"
     • "1024x1792"
     • "1792x1024"

4. model (enum)

   • Purpose: The OpenAI model to use for generating the image.
   • Options:
     • "dall-e-3"
     • "dall-e-2"

Function Stack

1. OpenAI API Request

• Endpoint: https://api.openai.com/v1/images/generations
  • Purpose: Sends a POST request to the OpenAI API with the prompt and image size parameters.

2. Preconditions

• Condition: openai_api.response.status == 200
  • Purpose: Ensures that the request was successful (HTTP 200 status code).

3. OpenAI API Response

• Create Variable: response
  • Purpose: Stores the response from OpenAI API, which contains the URL of the generated image.

Response

• The function returns the generated image URL or image content.

Success response

{
   "image_url": "https://api.openai.com/v1/images/abcd1234"
}

Error response

{
  "message": "Incorrect API key provided: ssk-None*********************************************GQPD. You can find your API key at https://platform.openai.com/account/api-keys."
}

Example

Input

• Headers:
  • Authorization: Bearer openai_api_key
• Body:

  {
    "prompt": "A futuristic city with flying cars",
    "size": "1024x1024",
    "model": "DALL-E"
  }
  

Output

{

   "image_url": "https://api.openai.com/v1/images/abcd1234"

}