When calling gemini-3-pro-image-preview from my AWS Lambda Function, I consistently receive:
“Unable to show the generated image. The model could not generate the image based on the prompt provided. You will not be charged for this request. Try rephrasing the prompt. If you think this was an error, send feedback.”
When I test with the exact same API payload locally, I don’t see this error. This appears to be a cloud runtime error.
Has anyone seen IMAGE_OTHER only from a cloud runtime? Any guidance on why identical payloads would be refused in Lambda but not locally, and how to avoid this? I’d appreciate any insight from Google folks or the Google AI community! Thanks.