Models/NanaBanana 2.1
MODEL · IMAGENEW

NanaBanana 2.1

Google's newest Nano Banana: fast, sharp edits and up to 10 reference images at a fixed price per picture, from 1K to 4K. A good default for iteration, edits and quick drafts.

CAPABILITIES

What it can
do well.

  • ✓Generate from text promptsupported
  • ✓Edit existing imagessupported
  • ✓Reference image inputup to 10 refs
  • ✓In-image text renderingsupported
  • ✓Inpaint with masksupported
  • ✓Expand canvassupported
  • ✓Native 4K output4K from 18 credits
  • ×Video generationnot supported

Prompts that hit.

3 PATTERNS · FROM THE STUDIO
PATTERN · ITERATE

"Same as last but [tweak], keep everything else identical."

Cheap to chain — perfect for refinement loops.

PATTERN · I2V SETUP

"Image-to-image: take this reference and output the same scene with [variation]."

Strong at preserving composition while swapping local details.

PATTERN · BATCH

"Generate 12 variants of [subject], each with a different [dimension: lighting / angle / style]."

A low per-image cost makes batch ideation viable.

ABOUT THIS MODEL

FAQ.

Q.01

When should I choose NanaBanana 2.1?

When your request plays to NanaBanana 2.1's strengths. Name it in your message or pick it in the composer; FlowPix never switches models on its own, and uses its default image model when you choose none.

Q.02

Can I pin this model as default?

Yes. The model picker in any chat lets you pin per-turn or per-session. Set as default in /settings.