Nano Banana 2 generated hero artwork

Nano Banana 2

Fast ideas. Precise images.

Bring advanced world knowledge, image quality and visual reasoning into one fast creative workflow. Generate new visuals or transform existing images with Nano Banana 2 through DreamAPI.

Capabilities

Generate. Edit. Restyle.

One image model for fast creation and precise, reference-led editing — at any size, with text that reads.

Precise editing

Change the mood, shift day into night, explore a new camera angle or redirect focus while keeping the parts of the image that already work.

Reference style

Bring a texture, color language or visual style from a reference image into a new subject. Explore distinct aesthetics while preserving the creative idea underneath.

Multi-size output

Adapt a finished idea for the format where it will appear. Reframe the composition for landscape, square or portrait placements while keeping the details that matter.

Text rendering

Create logos, invitations, posters, comics and other text-led visuals with clearer lettering. Nano Banana 2 can place words inside the image in many languages.

Showcase

Make the wild idea
feel finished.

Move from a prompt or source image to a polished visual, then keep refining the details without rebuilding the concept from scratch.

Precise editing

Dial in
every detail.

Change the mood, shift day into night, explore a new camera angle or redirect focus while keeping the parts of the image that already work.

Nano Banana 2 precise image edit example 1
Nano Banana 2 precise image edit example 2
Nano Banana 2 precise image edit example 3
Nano Banana 2 precise image edit example 4
Nano Banana 2 precise image edit example 5
Nano Banana 2 precise image edit example 6
Reference style

Style applied
in seconds.

Bring a texture, color language or visual style from a reference image into a new subject. Explore distinct aesthetics while preserving the creative idea underneath.

Nano Banana 2 reference style example 1
Nano Banana 2 reference style example 2
Nano Banana 2 reference style example 3
Nano Banana 2 reference style example 4
Multi-size output

One visual.
Many sizes.

Adapt a finished idea for the format where it will appear. Reframe the composition for landscape, square or portrait placements while keeping the details that matter.

Text rendering

Your words,
placed just right.

Create logos, invitations, posters, comics and other text-led visuals with clearer lettering. Nano Banana 2 can place words inside the image in many languages.

Nano Banana 2 text placement example 1
Nano Banana 2 text placement example 2
Nano Banana 2 text placement example 3
Developer API

API now available.

Use Nano Banana 2 in DreamAPI for text-to-image and image-editing workflows. The live workspace provides the current endpoint, authentication fields and response schema.

01

Add prompt & image

Send a prompt plus optional source or reference images in one JSON request.

02

Submit the task

Submit the job to the DreamAPI workspace and let it render.

03

Retrieve the result

Poll the task status and download the generated image.

Model IDgemini-3.1-flash-image
InputsPrompt + optional images
WorkflowsGenerate / edit / restyle
DeliveryDreamAPI task workflow
View API documentation
gemini-3.1-flash-image
const image = await dreamapi.images.generate({
  model: "gemini-3.1-flash-image",
  prompt: "Turn this product photo into a
  cinematic night campaign while preserving
  the product shape and label text.",
  images: ["https://example.com/source.png"]
});
curl https://api.newportai.com/v1/images/generations \
  -H "Authorization: Bearer $DREAMAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "prompt": "Turn this product photo into a cinematic night campaign...",
    "images": ["https://example.com/source.png"]
  }'
Workflows

One model.
Two workflows.

Start from words or start from an image. Nano Banana 2 supports both paths through one DreamAPI workspace.

StepGenerateEdit
Start withA written promptA prompt plus an image
DirectSubject, scene, action and styleMood, camera, focus, objects or background
Reference useGuide texture, color or aestheticPreserve details while changing the rest
Good forConcepts, campaigns, posters and illustrationsVariants, restyling, resizing and photo changes
OutputA new generated imageA transformed version of the source
Pricing plans

Top up credits.
Pay as you generate.

One credit pool for every model on DreamAPI — video, image, avatar and editing. Buy a pack, then spend credits at the per-model rates below.

Credit packs are purchased on the DreamAPI pricing page.

Pricing

Nano Banana 2 pricing.

Credits are charged per generated image and scale with output resolution.

gemini-3.1-flash-image — per generated image

ModelResolutionCredits
gemini-3.1-flash-image51215
gemini-3.1-flash-image1K20
gemini-3.1-flash-image2K30
gemini-3.1-flash-image4K40

Credits per generated image. Current DreamAPI billing rules apply.

FAQ

Before your
first image.

What is Nano Banana 2?+

Nano Banana 2 is Google's latest image generation and editing model. Google describes it as combining advanced world knowledge, quality and reasoning with the speed needed for rapid creative work.

Can Nano Banana 2 edit an existing image?+

Yes. Provide an image and describe the change in natural language. You can adjust the mood, lighting, camera angle, focus, background, objects or overall style while retaining details you want to keep.

Can it use a reference image for style?+

Yes. A reference can guide texture, color or visual style, letting you reimagine a subject without starting from scratch.

Can Nano Banana 2 create text inside images?+

Yes. Google highlights clear text placement for logos, invitations, posters and comics, including words in many languages.

How much does Nano Banana 2 cost on DreamAPI?+

The gemini-3.1-flash-image model uses 15 credits at 512 resolution, 20 credits at 1K, 30 credits at 2K and 40 credits at 4K per generated image.

Can I create different aspect ratios?+

Nano Banana 2 can adapt a visual to different formats while preserving important details. Use the current DreamAPI workspace to see the supported size and aspect-ratio options.

How do I use Nano Banana 2 through DreamAPI?+

Open the Nano Banana 2 workspace, enter a prompt, add source or reference images when needed, submit the task and retrieve the generated result using the documented DreamAPI flow.

How does Google identify AI-generated images?+

Google states that Gemini image outputs include an invisible SynthID watermark and a visible watermark to distinguish AI-generated visuals from original human artwork.

Bring the idea
into focus.

Generate, edit and adapt polished images with Nano Banana 2 through one production-ready DreamAPI workflow.