caption_image
Generate descriptive captions for images from URLs or local files using AI vision models. Describe key subjects, scenes, and moods in concise language.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| backend | No | ||
| file_path | No | ||
| image_url | No | ||
| local_model_id | No | ||
| prompt | No | Write a concise, vivid caption for this image. Describe key subjects, scene, and mood in 1-2 sentences. |
Input Schema (JSON Schema)
{
"properties": {
"backend": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Backend"
},
"file_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "File Path"
},
"image_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Image Url"
},
"local_model_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Local Model Id"
},
"prompt": {
"default": "Write a concise, vivid caption for this image. Describe key subjects, scene, and mood in 1-2 sentences.",
"title": "Prompt",
"type": "string"
}
},
"title": "caption_imageArguments",
"type": "object"
}