Gemini Multimodal Error
I'm facing an issue with gemini-pro-vision model to analyze an image. Does anyone know how to resolve this?
1 Reply
Hi @yirda, this seems an issue with the image or prompt, you can refer the max supported requirements for image and prompt here - https://ai.google.dev/docs/gemini_api_overview#image_requirements.
Google AI for Developers
Gemini API Overview | Google AI for Developers