Nano Banana AI Image Generator & Editor
Nano Banana is the nickname for Google's Gemini 2.5 Flash image model. It is preselected below: describe an image to generate it, or switch to Image to Image, upload a photo and say what to change.
- credits per image
- 5credits per image
- measured, text to image
- ~35smeasured, text to image
- reference images it can read
- 16reference images it can read
- free credits on sign-in
- 20free credits on sign-in
Sign in to start — new accounts get 10 free credits, no card.
Example prompts for Nano Banana
The same prompts are behind the “Try an example” button in the input box; each click loads the next one.
Product shot
Matte black ceramic mug on a pale linen surface, soft window light from the left, shallow depth of field, editorial product photography
Portrait
Close-up portrait of an older woman laughing, natural window light, film grain, 85mm lens, shallow depth of field
Landscape
Misty pine forest at dawn, low fog between the trunks, cold blue light, wide shot
Made with these models
Images generated on this site with the same models.
Why Nano Banana on AI Image Tools
Follows the instruction, keeps the rest
Swap a background, change an outfit, add or remove an object, restyle a photo: the face, pose and framing stay put. It is the most literal instruction-follower of the models here.
Several reference images at once
It reads more than one input image, which is why the Virtual Try-On tool runs on it: one photo of the person, one of the garment.
As cheap as any model here
5 credits per image, the same as FLUX.1 Kontext. A text prompt took 31 to 39 seconds end to end across our runs.
Slower for edits, so choose deliberately
Editing an uploaded photo can take several minutes when the model is busy. If you need a fast edit, pick FLUX.1 Kontext from the same dropdown.
Every image model in one place
Pick any of these from the Model menu above; the price is shown before you generate. Each name links to what that model is good at. Compare every tier.
Z-Image Turbo
Alibaba · cheapest and fastest, text-to-image only
1 credits per image
Seedream 5 Pro · 1K
ByteDance · same model as 2K at half the price
9 credits per image
GPT Image 2.5 Flare · 2K
OpenAI · same price as Sunburst, tuned for speed and volume
13 credits per image
Qwen Image 3 · 2K
Alibaba · strong at readable text inside the image
6 credits per image
Nano Banana
Google Gemini 2.5 Flash · fastest, cheapest
5 credits per image
Nano Banana 2.1 · 1K
Google · newest Nano Banana, sharper text, banner ratios
10 credits per image
Nano Banana 2.1 · 2K
Google · same model at 2K
15 credits per image
Nano Banana 2.1 · 4K
Google · for print or heavy cropping
23 credits per image
Ideogram V3 · Turbo
Ideogram · text inside the image, fastest tier
5 credits per image
Ideogram V3 · Balanced
Ideogram · text inside the image, posters and logos
9 credits per image
Ideogram V3 · Quality
Ideogram · text inside the image, highest detail
13 credits per image
FLUX.1 Kontext
Black Forest Labs · fastest, about 5s per image
5 credits per image
Seedream 5 Lite
ByteDance · good at Chinese text and posters
7 credits per image
Seedream 5 Pro · 2K
ByteDance · most photorealistic, highest detail
18 credits per image
GPT Image 2 · 2K
OpenAI · good with text in images, half the price of 2.5
7 credits per image
GPT Image 2 · 4K
OpenAI · for print or heavy cropping
10 credits per image
GPT Image 2.5 · 2K
OpenAI · newest, better instruction following
13 credits per image
GPT Image 2.5 · 4K
OpenAI · newest, highest resolution
20 credits per image
Nano Banana specifications
- Model
- Google Gemini 2.5 Flash image ("Nano Banana")
- Modes
- Text to Image and Image to Image, in the generator above
- Input
- A text prompt, or a photo up to 10 MB plus a prompt; several reference images for tools like Virtual Try-On
- Sizes
- 1:1, 16:9, 9:16, 4:3, 3:4
- Batch
- 1, 2 or 4 images per run
- Output
- PNG, saved to My Creations
- Cost
- 5 credits per image
- Time
- 31 to 39 seconds for text-to-image across our runs; edits of an uploaded photo can take several minutes when the model is busy
- Free plan
- 10 credits on sign-in; free downloads carry a small watermark
How to use Nano Banana
- Step 1
Sign in
New accounts get 10 free credits, enough for 2 Nano Banana images.
- Step 2
Pick a mode and describe it
Text to Image for a new picture, Image to Image to change a photo you upload. Say what you want and what should stay the same.
- Step 3
Generate and download
Results are saved to My Creations. Free-plan downloads carry a small watermark.
How to write a prompt for Nano Banana
Be literal
It does what you say. "Replace the sky with a clear dusk sky, keep everything else" beats "make it moodier".
Name what stays
For edits, list what must not change: face, pose, background, text.
Reference images
When a tool accepts more than one image, say which is which: "the garment in image 2 on the person in image 1".
Text in the image
Put the exact words in quotes and keep them short.
Pricing
Every tool draws from one balance.
No hidden fees • Cancel anytime • Unused credits roll over
Swipe to compare plans →
Nano Banana: frequently asked questions
What is Nano Banana?
The community nickname for Google's Gemini 2.5 Flash image model, known for editing photos from plain-language instructions while keeping the rest of the picture intact.
Is Nano Banana free here?
Every image costs 5 credits, and new accounts get 10 credits on sign-in, so the first 2 images are free. Free-plan downloads carry a small watermark.
Why are edits slower than generations?
Across our runs a text prompt took 31 to 39 seconds end to end. Editing an uploaded photo goes through a different endpoint that can queue for several minutes when the model is busy. FLUX.1 Kontext edits in roughly 20 to 30 seconds if you would rather not wait.
Can it keep a face consistent across edits?
That is its strength: it keeps identity, pose and framing when you tell it what to change. Add "keep the face exactly the same" for portraits.
How is it different from FLUX.1 Kontext?
Same price. Kontext is faster and takes a single image; Nano Banana follows longer instructions more literally and can read several reference images, which is what multi-image tools need.
How is it different from Nano Banana 2.1?
Nano Banana 2.1 is Google's newest generation. It starts at 10 credits instead of 5 and adds 2K and 4K output and wider banner ratios. See the Nano Banana 2.1 page; both are in the same model menu.
What happens if a generation fails?
You are only charged when an image comes back. A failed or timed-out run costs nothing.
Generate or edit with Nano Banana
The generator at the top of this page has it preselected. Start with your free credits.
The other models
All of them are in the same dropdown, and one credit balance covers every one.
- GoogleNano Banana 2.1Google's newest Nano Banana. 1K to 4K and 14 aspect ratios down to 1:8; Google says it renders text better than 2.
- Black Forest LabsFLUX.1 KontextThe fastest editing model here, and the default behind Image to Image and the seven redraw tools.
- ByteDanceSeedream 5ByteDance's model, in a cheap Lite tier and a 2K Pro tier. The most photorealistic option here.
- OpenAIGPT ImageOpenAI's models in four tiers, up to 4K. The strongest here when the picture has to contain readable text.
- IdeogramIdeogramIdeogram V3, built around readable text inside the image: posters, logos, social graphics. From 5 credits.