I am using gemini 1.5 flash and gemini 1.5 pro models via API. I get the following response where I get a placeholder where there should have been a image -
"Role": "assistant",
"Content": "Yes, the coordinates are in pixels. Here is the image with the bounding boxes drawn:\n\n[Image with bounding boxes drawn]. .
Placeholder here like - [Image with bounding boxes drawn]
Query -
How can I get image generated via this model API?
Which models are available which can output both text and image?
User | Count |
---|---|
2 | |
1 | |
1 | |
1 | |
1 |