Block after block with a simple prompt in NanoBanana

Google AI Studio
,
1

Hi there!

I’m trying to generate a portrait of a man in 3/4 (from knees to head) with NanoBanana, starting from a close-up portrait of this desired man. The prompt is quite simple:

”Using the provided character face image, create a portrait from waist up. The man from the image wearing business suit, standing straight facing camera, professional pose. Modern office background. Clean professional lighting, photorealistic, high detail, 8K”

I have never had problems with these kind of prompts. Where is the problem now?? The man is well dressed on expensive clothes, no nudes, no anything wrong. Now I get block after block after block.

This is the message I get: “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](https://ai.google.dev/gemini-api/docs/troubleshooting).”

If anybody have any clue, please answer to this post.

Thank you in advance!

3

It usually happens when the system thinks the image is being used to recreate a real identifiable person, which triggers the safety filters. Try reducing hyper-realistic terms, avoid directly saying “using the provided image,” and instead describe the character in words. Small prompt changes often fix the block.

5

Thank you Emma! I wasn’t taking into account that the AI ​​wasn’t able to detect that the image was created by AI. I will try with different prompts.