How can you use the API to merge two pictures?

API
4

Yes. You can use multiple base64 images as one user message, and can interleave text with the images sequentially.

This is the style of a complete app request with multiple base64 images that only sends to a DALL-E API as strict response format.

from openai import OpenAI
client = OpenAI()

response = client.chat.completions.create(
  model="gpt-4o",
  messages=[
    {
      "role": "system",
      "content": [
        {
          "type": "text",
          "text": "You use your computer vision on user images to make new AI images."
        }
      ]
    },
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Take the style from this image:"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/png;base64,..."
          }
        },
        {
          "type": "text",
          "text": "Take the subject from this image:"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/png;base64,..."
          }
        },
        {
          "type": "text",
          "text": "Examine attached images. Synthesize a new dalle image, with combined description."
        }
      ]
    }
  ],
  response_format={
    "type": "json_schema",
    "json_schema": {
      "name": "dalle_output",
      "strict": True,
      "schema": {
        "type": "object",
        "properties": {
          "prompt": {
            "type": "string",
            "description": "A textual description of the image to be generated. Target 200 words."
          },
          "size": {
            "type": "string",
            "description": "The size of the generated image. 1792 is 'wide'.",
            "enum": [
              "1024x1024",
              "1792x1024"
            ]
          }
        },
        "required": [
          "prompt",
          "size"
        ],
        "additionalProperties": False
      }
    }
  },
  temperature=0.5,
  max_completion_tokens=1500,
  top_p=0.9,
)
1 Like