Skip to main content
Every generation in Studio runs through one of two prompt-processing modes. You toggle between them in the chat settings menu.

​
Memo Magic (default)

The agent takes your prompt and enhances it before calling the image model. A short request like “a bar of soap” becomes a rich, cinematic prompt with composition, lighting, camera angle, textures, and atmosphere — structured using the Nano Banana framework that the image model responds best to. Use Memo Magic when you want:
  • Production-quality results from short prompts
  • The agent to act as a creative director
  • Cinematic polish without having to write it yourself
Example:
  • You type: a bar of soap
  • Memo Magic sends: a full structured prompt with subject, composition, lighting setup, camera/lens choice, and style direction tuned to what that subject needs

​
Simple

The agent sends your exact words to the image model, verbatim. No rewriting, no embellishment, no added detail. What you type is what the model sees. Use Simple when you:
  • Are testing prompt fidelity
  • Have written a carefully-crafted prompt yourself
  • Want full control over every word
  • Are comparing model behaviour for the same raw input
Example:
  • You type: a bar of soap
  • Simple sends: a bar of soap

​
Confirmed briefs always use Memo Magic

Simple mode only applies to direct, single-shot prompts. When you confirm a creative brief — whether it’s a parallel campaign or a sequential storyboard — the agent’s crafted scene prompts are always used, because the brief is the prompt you co-wrote and confirmed with the AI. Toggling Simple on doesn’t downgrade your confirmed brief back to the raw sentence you started with. This means:
  • Single prompt + Simple on → your words, verbatim
  • Single prompt + Memo Magic on → AI-enhanced prompt
  • Confirmed brief (any toggle, any continuity mode) → the brief’s crafted per-deliverable prompt

​
Switching between modes

The toggle lives in the Studio chat settings, next to the model selector and the Create / Brainstorm mode toggle. It persists across turns in the same conversation but doesn’t affect previously-generated images. Changing the mode mid-conversation only affects future generations. Your existing nodes stay exactly as they were generated.