Nano Banana 2
A Google image model for reference-heavy editing, product preservation, typography, relighting, and scene transformation workflows.
Key facts
| Developer | |
|---|---|
| Availability on Banana Pie | Available now |
| Credits from | 40 credits / image |
| Reference images | Up to 8 |
Nano Banana 2 is positioned for complex image workflows that combine multiple references with text, lighting, layout, or scene edits. Its 8-reference capacity and 4K ceiling are concrete advantages, but the published evidence contains only one run per scenario, so consistency remains unproven.
Strengths
- Multi-reference capacity
Support for up to 8 reference images gives creators room to combine identity, garment, object, and scene inputs in one workflow.
- High-resolution output
The 4K maximum resolution supports deliverables that need more output detail or room for downstream layout work.
- Editing-oriented scope
The evidence suite covers text replacement, multilingual typography, structured UI graphics, advertising composition, relighting, and outpainting.
- Product workflow coverage
Dedicated scenarios cover product materials, product preservation, scene changes, and advertising composition.
Limitations
- Limited repeatability evidence
Each published scenario contains only one run selected by the automatic only-run rule, so the evidence does not establish consistency across repeated generations.
- Variable turnaround
Observed runtimes vary across the published scenarios, so plan for workflow-dependent turnaround rather than assuming uniform generation time.
- No linked official documentation
No official source URLs were supplied, which limits verification beyond the listed runtime facts and scenario evidence.
- Higher entry cost for simple work
The minimum listed cost is 40 credits, which may be unnecessary for straightforward prompts that do not use its reference or editing capabilities.
Choose Nano Banana 2 when
- You need to coordinate several source images in one generation, with support for up to 8 references.
- You are preparing product, advertising, garment, identity, or scene-editing work.
- Your workflow includes typography, text replacement, relighting, outpainting, or structured graphics.
- You need output up to 4K and can validate important details before scaling production.
Consider an alternative when
- You only need a straightforward prompt-to-image result without references or targeted edits.
- You need proven consistency across repeated runs rather than evidence from one selected run per scenario.
- You require official documentation or source links before adopting a model.
- Your credit budget does not accommodate a minimum listed cost of 40 credits.
Real-world results
Same fixed prompts we run on every model - one run each, published exactly as generated.
Prompt
A premium product photograph of exactly one transparent rectangular perfume bottle, half filled with amber liquid, standing upright on wet black stone. Light comes from the upper left, creating coherent refraction, a contact shadow, and one subtle reflection. No text, logo, plants, or extra objects.
Settings
- Resolution: 1K
- Aspect Ratio: 1:1
Prompt
Design a clean cream-colored vertical event poster. Show exactly four centered text lines and no other text: "MOONLIGHT MARKET", "月光市集", "18 OCT", and "RIVER HALL". Render "月光市集" in red and all other lines in black.
Settings
- Resolution: 1K
- Aspect Ratio: 2:3
Prompt
A photorealistic close-up of an adult potter shaping a clay bowl on a spinning wheel. Both hands are fully visible, each with five natural fingers touching the clay. No other people or hands. Soft window light.
Settings
- Resolution: 1K
- Aspect Ratio: 3:4
Prompt
On a matte gray table, exactly three red wooden cubes form a row on the left, exactly two blue glass spheres sit on the right, and one yellow ceramic mug stands centered behind them. The mug handle points right. No other objects or text.
Settings
- Resolution: 1K
- Aspect Ratio: 4:3
Prompt
Create a vertical social ad for a fictional running shoe named AERO. Keep the top 15 percent empty. Directly below it, place the headline "RUN LIGHT" in the upper-left. Show exactly one silver shoe in the lower-right, an orange trail curving from the bottom-left, and a round badge reading "42 KM". No other shoes or text.
Settings
- Resolution: 1K
- Aspect Ratio: 9:16
Prompt
Create a clean horizontal pricing comparison graphic titled "CHOOSE YOUR PLAN". Use exactly three equal columns labeled "STARTER", "PRO", and "TEAM". Under each column, show exactly three aligned rows labeled "PROJECTS", "STORAGE", and "SUPPORT", followed by one blue button labeled "SELECT". White background, dark navy text, no additional columns or text.
Settings
- Resolution: 1K
- Aspect Ratio: 16:9
Reference images
Prompt
Use Reference 1 as the base tabletop scene. Replace the red mug with the exact dark navy-blue mug from Reference 2 in the same position and orientation. Replace the folded white towel with the exact green-and-white striped napkin from Reference 3 in the same folded area. Replace the green pear with exactly one orange from Reference 4 in the same position. Replace the blue notebook with the exact mustard-yellow hardcover notebook from Reference 5 in the same position. Add exactly the two lemons from Reference 6 to the right of the mug. Preserve the wooden table, camera, framing, wood grain, lighting, shadows, and all other spatial relationships from Reference 1. Do not copy the white product backgrounds from References 2–6, duplicate any asset, or add other objects.
Settings
- Resolution: 1K
- Aspect Ratio: 4:3
Reference images
Prompt
Replace only the sign text with exactly "NIGHT OWL". Preserve the original font style, spacing, perspective, sign material, lighting, and everything else.
Settings
- Resolution: 1K
- Aspect Ratio: 3:2
Reference images
Prompt
Use the portrait in Reference 1 for the person and the isolated jacket in Reference 2 for the garment. Dress the person from Reference 1 in the exact jacket shown in Reference 2. Preserve the person's identity, face, expression, skin, hair, hands, pose, body proportions, background, framing, and lighting from Reference 1. Preserve the jacket's material, color, collar, buttons, pockets, and sleeve patch from Reference 2. Do not copy the ghost mannequin or white product background.
Settings
- Resolution: 1K
- Aspect Ratio: 3:4
Reference images
Prompt
Change the lighting to warm golden-hour sunlight entering from the left window. Do not move, add, remove, or redesign any object. Update highlights and shadows coherently.
Settings
- Resolution: 1K
- Aspect Ratio: 16:9
Reference images
Prompt
Expand the canvas to a 16:9 landscape by naturally continuing the beach, ocean, and sky on both sides. Keep the complete original image centered without cropping, stretching, letterboxing, or modifying it.
Settings
- Resolution: 1K
- Aspect Ratio: 16:9
Reference images
Prompt
Place the sneaker on a wet outdoor basketball court at dusk. Preserve the exact sneaker shape, black geometric side mark, materials, stitching, sole geometry, and camera angle. Add physically coherent contact, reflections, and dusk lighting.
Settings
- Resolution: 1K
- Aspect Ratio: 1:1
Credits & pricing
Nano Banana 2 starts at 40 credits. In practice, that is the lowest listed entry cost for a generation, so it makes more sense when you need its 8-reference capacity, 4K output, or editing-oriented workflow coverage than for a basic prompt.
Frequently asked questions
How many reference images can I use?
Nano Banana 2 supports up to 8 reference images, making it relevant to identity, garment, object, and product-preservation workflows.
What is the maximum output resolution?
The listed maximum resolution is 4K.
Can it handle text inside images?
The evidence covers multilingual typography and in-image text replacement, but each scenario has only one selected run. Treat text-heavy work as something to verify before committing credits to a larger batch.
Is it suitable for product and advertising images?
The test suite includes product material and lighting, advertising composition, scene relighting, scene changes, and product preservation. The available evidence shows workflow coverage, not repeatability across multiple runs.
When should I choose Nano Banana 2 over another image model?
Choose it when you need up to 8 references, 4K output, or editing workflows that combine subjects, garments, products, text, and scene changes. Use a simpler option when those controls are unnecessary.
Related comparisons
- nano banana 2 vs seedream 5 pro
- nano banana vs nano banana 2
- nano banana 2 vs nano banana pro
- gpt image 2 vs nano banana 2
How we test & disclosure
Conclusions are based on a fixed prompt suite spanning the listed scenarios and their published selections; because each selection came from an automatic only-run rule, the results indicate workflow coverage rather than comparative or repeatability evidence.
Banana Pie sells paid access to this model alongside other models in one studio. Our verdicts come from tests run through the same pipeline our users get.