Create images with Nano Banana

Nano Banana is a lineup of image generation models from Google built on the Gemini Flash reasoning engine. Unlike typical diffusion models, Nano Banana "thinks through" the scene first, analyzing the composition's logic, physics, and spatial relationships, and only then renders the result. Flami offers Nano Banana Pro and Nano Banana 2.

They're two versions of the same family with different priorities. Nano Banana Pro is the flagship, with the deepest reasoning, precise typography, and the highest quality for complex compositions. Nano Banana 2 is a speed-optimized version with nearly the same quality, but 2 to 3 times faster and cheaper. Pro is for final layouts, Banana 2 is for quick iteration and generating in bulk.

The key difference is font rendering. Nano Banana writes text in the frame accurately, without "AI mush," which matters for posters, packaging, UI mockups, and ads. The model also understands real-world physics better than most (reflections, lighting, gravity) and keeps up to five consistent characters in one scene.

The price depends on the version you pick (Pro costs more, Banana 2 is cheaper) and the resolution. On the Start and Pro plans, you get a monthly credit pack with a fixed price per image. See the pricing section for the exact cost.

From 512 pixels up to 4K with intelligent upscaling on a 16-bit color channel. Formats: 16:9, 9:16, 1:1, 4:3, 3:4, and more. Great for social media posts, ad layouts, and print materials alike.

Yes, that's one of Nano Banana's key strengths. The model accurately renders fonts, captions, headlines, logos, and any text in the frame. It works in dozens of languages. Great for packaging, posters, UI mockups, and ads where garbled AI text isn't an option.

Yes. Upload a reference image of the character, and Nano Banana keeps their face, outfit, and style consistent across all generations. The model supports up to five consistent characters within one project, great for storyboards, serial campaigns, and multi-story materials.

Yes. Nano Banana works in image-to-image mode: upload a finished image, describe what to change, and the model makes the edit carefully without touching the rest. Great for swapping objects, changing the background, or making local style tweaks.

10 to 30 seconds, depending on the version and scene complexity. Nano Banana 2 takes about 10 seconds, while Nano Banana Pro takes up to 30 seconds for its deeper reasoning mode.

No. Both Nano Banana models are available right inside Flami with a regular Start or Pro subscription. No need to sign up with Google or connect to the Gemini API: all models live in one account.

Every generation uses credits. On a paid plan, you get a monthly credit pack and spend it on creating images. If you run out, you can buy extra credits as a one-time purchase.

Credits refresh automatically at the start of each billing period. Unused credits from last month don't carry over, so if you didn't use up your allowance, you can switch to a smaller plan next month.

You can buy extra credits as a one-time purchase or switch to a bigger plan. The new pack becomes available right after payment, no need to wait until the end of the month.

Yes, anytime. In the Subscriptions section, turn off auto-renewal: your current paid period runs its course, and nothing gets charged after that.