generate_image
Create custom images from text prompts using OpenAI's DALL-E 3 model. Specify size, quality, and style, and save directly to the local filesystem for seamless integration.
Instructions
Generate an image using OpenAI's DALL-E 3 model based on a text prompt
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| filename | No | Optional custom filename (without extension) | |
| prompt | Yes | The text prompt describing the image to generate | |
| quality | No | Image quality (standard or hd) | standard |
| size | No | Image size (1024x1024, 1024x1792, or 1792x1024) | 1024x1024 |
| style | No | Image style (vivid or natural) | vivid |
Input Schema (JSON Schema)
{
"properties": {
"filename": {
"description": "Optional custom filename (without extension)",
"type": "string"
},
"prompt": {
"description": "The text prompt describing the image to generate",
"type": "string"
},
"quality": {
"default": "standard",
"description": "Image quality (standard or hd)",
"enum": [
"standard",
"hd"
],
"type": "string"
},
"size": {
"default": "1024x1024",
"description": "Image size (1024x1024, 1024x1792, or 1792x1024)",
"enum": [
"1024x1024",
"1024x1792",
"1792x1024"
],
"type": "string"
},
"style": {
"default": "vivid",
"description": "Image style (vivid or natural)",
"enum": [
"vivid",
"natural"
],
"type": "string"
}
},
"required": [
"prompt"
],
"type": "object"
}