Cloudinary Generative AI Playground
Generative Image Captions
Image-to-text models provide contextual descriptions of an image.
Note: The underlying AI technology behind these features is still experimental, the quality of results may vary.
JSON Response{
"asset_id": "a30dc93a8580b272f05db9f3d47dbeab",
"public_id": "1mqow1pnmgfxkkoackdp",
"info": {
"detection": {
"captioning": {
"status": "complete",
"data": {
"caption": "false"
},
"model_version": 1,
"schema_version": 1
}
}
},
"original_filename": "file.jpg"
}
Learn More About This Feature
Visit the Documentation
Read the Blog Post