Nano Banana 2 for Virtual Try-On & Image Editing

Nano Banana 2 virtual try-on through a partner API with up to 4K output.

Upload a photo of a person and a photo of an outfit. The model dresses the person in the referenced clothing while preserving their face, body, pose, and background. Clothing details, colors, fit, and texture carry over from the reference. Nano Banana 2 is an API model by Google DeepMind (also known as Gemini 3.1 Flash Image), so each run costs additional credits from your API wallet. No API key needed. Floyo handles the connection.

The prompt is pre-filled. Upload two images and hit run.

How do you use Nano Banana 2 for virtual try-on?

Upload a photo of the person you want to re-dress and a clear shot of the outfit. The model reads both images, keeps the person's identity and pose, and generates a new image with them wearing the referenced clothing. The prompt is already written. Change nothing on your first run.

Image 1 (Model) The person you want to re-dress. Face, pose, and background carry over to the result. A clear, well-lit photo with the full body visible works best. The workflow labels this "Model" but it works for any subject when you rewrite the prompt.

Image 2 (Clothes) The outfit you want applied. A front-facing product shot with even lighting gives the cleanest results. Busy backgrounds in the clothing image can bleed into the output. This input is optional for non-try-on edits where you only need one reference.

Prompt Pre-filled with a virtual try-on instruction. For your first run, leave it alone. If the result misses something, rewrite the prompt before touching any other setting. You can also use the prompt for non-try-on edits: describe any change you want and the model will apply it. For reference-image edits, describe only the change. The model sees your images already.

Resolution (default: 2K) Output sharpness. 2K is a good starting point. Higher resolutions cost more per run. Quality can vary on fine detail when pushing past 2K.

Aspect Ratio (default: 16:9) Shape of the output image. Match this to your input images to reduce cropping.

Output Format (default: PNG) Choose PNG or JPEG. PNG keeps full quality. JPEG produces smaller files.

Web Search (default: off) Turn on to let the model pull real-world references while generating. Useful for prompts that reference real brands, logos, or specific styles.

Seed (default: random) Controls randomness. Want to reproduce a result you liked? Lock the seed number from that run. Want variety? Leave it on random.

What is Nano Banana 2 good for?

Nano Banana 2 is an API model by Google DeepMind, also known as Gemini 3.1 Flash Image. It takes up to three reference images, follows prompts well, generates fast, and outputs up to 4K. It is strong at text rendering inside images and subject consistency across references.

E-commerce teams can shoot a model once and swap outfits across an entire catalog without rebooking a studio. Upload the model photo, swap in each product shot, and build a full lookbook from a single session. The API handles generation, so there are no GPU settings to tune.

Stylists and fashion designers can test combinations before producing samples. See how a fabric reads on a body without sewing anything.

The model also works for non-clothing edits. Rewrite the prompt and it becomes a general image editor that takes reference images as context. Background swaps, logo placement, compositing, and style transfer all work through the same pipeline. A third image input is available but not connected in this layout. Wire it up if you need three references.

This is a partner API workflow. Each run costs additional credits from your API wallet on top of your Floyo plan. Generation time depends on server load but is typically a few seconds per image. The model uses closed weights accessed through Floyo's partner API. No local download is available.

FAQ

What resolution should I use for Nano Banana 2 virtual try-on? Start at 2K. For most try-on work, 2K gives clean results without high cost. Higher resolutions are available up to 4K but quality gains on fine detail can vary. Going higher also costs more per run.

Can I use Nano Banana 2 for edits besides virtual try-on? Yes. Rewrite the prompt to describe any edit: background swaps, object placement, style transfer, logo application, or compositing. The workflow supports up to three reference images, though only two are connected in this layout. The second reference is optional for single-image edits.

Does Nano Banana 2 cost extra? Yes. This workflow calls an external API through Floyo's partner connection. Each run costs additional credits from your API wallet. No separate API key is needed. Floyo handles the connection.

What is the web search setting for? When turned on, the model can pull real-world references while generating. This helps with prompts that mention real brands, logos, or specific styles the model might not have in its training data. For standard try-on work, leave it off.

How do I run Nano Banana 2 virtual try-on online? You can run Nano Banana 2 virtual try-on online through Floyo. No installation, no setup. Open the workflow in your browser, upload your inputs, and hit run. Free to try.