by GoogleImage
Nano Banana
11 models · from 76 credits
Models in the Nano Banana family
| Model | Mode | Price | Aspect ratios | |
|---|---|---|---|---|
| Nano Banana 2 Edit | Image edit | from 100 credits | — | Open → |
| Nano Banana 2 Reference to Image | Image | from 100 credits | 1:1 · 3:2 · 2:3 · 3:4 · 4:3 · 4:5 | Open → |
| Nano Banana 2 Text-to-Image | Text to image | from 100 credits | — | Open → |
| Nano Banana 2.1 EditNew | Image edit | from 83 credits | 1:1 · 3:2 · 2:3 · 3:4 · 4:3 · 4:5 | Open → |
| Nano Banana 2.1 Reference-to-ImageNew | Image | from 400 credits | 1:1 · 3:2 · 2:3 · 3:4 · 4:3 · 4:5 | Open → |
| Nano Banana 2.1 Text-to-ImageNew | Text to image | from 80 credits | 1:1 · 3:2 · 2:3 · 3:4 · 4:3 · 4:5 | Open → |
| Nano Banana Edit | Image edit | from 76 credits | 1:1 · 3:2 · 2:3 · 3:4 · 4:3 · 4:5 | Open → |
| Nano Banana Pro Edit | Image edit | from 175 credits | — | Open → |
| Nano Banana Pro Edit Ultra | Image edit | from 188 credits | — | Open → |
| Nano Banana Pro Text-to-image | Text to image | from 175 credits | — | Open → |
| Nano Banana Pro Text-to-image Ultra | Text to image | from 188 credits | — | Open → |
LUVI Prompt Engine rules for Nano Banana 2.1
TARGET MODEL: Nano Banana 2.1 (Google, gemini-nano-banana-2.1). It reads a brief the way a language model reads one: positively, in prose. There is no negative_prompt, no weighting and no style dial.
Rules that must hold
- Narrative prose, not tag stacks. Describe a scene a person could photograph or design: register → subject and action → setting → light → camera → in-image text → finish.
- Exclusions become presences that do NOT name the excluded thing: "no people, no cars" → "a quiet, deserted street", never "no cars" and never "empty of people and cars". Naming the unwanted thing can summon it.
- Aspect ratio and resolution are parameters. Never write "16:9", "widescreen", "4K" or "8k" into the prose — on a conflict the parameter wins and the words are wasted.
- In-image text: put every visible string in double quotes, exactly as it must read, and describe the type (weight, style, colour) and its placement in plain words. Never write the words "in quotes" or "quoted" — the model draws the quotation marks. Every other visible surface (signs, apparel, packaging, screens) is either given quoted copy or described as plain/blank; unquoted incidental lettering comes back as gibberish.
- Keep quoted copy verbatim. If it contains an em dash, the model draws it as a separate rule that splits the line: add OUTSIDE the quotes that the text stays on a single line with a literal em dash between the phrases. Example: a sign reading "Taze simit — İçeride çay var" on a single line, with a literal em dash between the two phrases.
- Non-English copy (e.g. Turkish İ ı ğ ş ç) is kept character-exact and LARGE in the frame; small lettering drops diacritics at any resolution.
- People: keep every physical detail the user gave (age, build, hair, wardrobe, expression) — never flatten a described person to "a man"; vague unnamed people drift toward real public-figure lookalikes. Keep distinct on-screen identities few; give extras varied faces or defocus them.
- Never ask for a transparent background — the model has no alpha. Ask for a plain seamless white background instead.
What works best
- Open with the operation and the deliverable: "Create an image: a photorealistic product photograph of …", "… an infographic poster …".
- State purpose and audience when known ("for an e-commerce product page", "suitable for a 4th grader").
- Many elements → order them in words: "First … Then … Finally …".
- When the user names light, lens or mood, phrase it concretely ("soft window light from the left" beats "cinematic lighting"). Do not add light directions, lenses, camera specs, scene elements (buildings, props, background figures) or wardrobe the user did not ask for — expand only what the user wrote.
- Prose over JSON: when the user supplies JSON, rewrite its content as prose — JSON loses counted details and soft details.
From the LUVI Prompt Engine rules for this family — the same rules the workspace rewriter and LUVI's MCP connector apply.
LUVI Prompt Engine rules for Nano Banana
Notes
- Nano Banana has no negative_prompt — describe positively (“an empty, deserted street”, not “no cars”). Naming what you don’t want can summon it into the frame.
- Weight syntax such as (word:1.3) is ignored; it only wastes prompt space.
- Keep to at most 5 distinct characters in one prompt.
From LUVI's verified rules for this family.