Google's Nano Banana Now Lets You Drop Yourself Into Any AI Video

Google just made it significantly less annoying to put yourself in AI-generated content. Gemini now supports persistent personal avatars: record your face and voice once, and you can drop yourself into any image or video scene without uploading a new selfie every time. The feature is rolling out today to Gemini app users in select countries, and it ties directly into Nano Banana, Google's viral image generation model.

What is Nano Banana, exactly?

The model powering Nano Banana is Gemini 2.5 Flash Image, Google's current-generation multimodal image model. The "Nano Banana" nickname was popularized by creators and AI content communities online as shorthand for Google's Gemini Flash Image model. The name stuck because the model punches well above its weight class for a free-to-access tool. It has since become the backbone of Gemini's entire personalized image stack.

Nano Banana refers to four distinct models available in the Gemini API, including Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image), the fastest and cheapest option engineered for velocity and scale. Nano Banana 2 pulls from the Gemini model's real-world knowledge base and is powered by real-time information and images from web search to more accurately render specific subjects.

The selfie problem it solves

Every time you wanted to generate an image of yourself with a previous AI tool, you had to manually upload a photo, describe your appearance in the prompt, and hope the model kept your likeness consistent. That friction adds up fast, especially if you're iterating across multiple styles or scenes.

The new avatar system eliminates that loop entirely. You can record your face and voice to create your avatar to use in Gemini Apps, and once created, use it when you create videos with Gemini Omni and streamline your content creation process. After the one-time setup, your avatar is attached to your Google account and callable from any prompt with a simple @[your Google username] mention.

How to set it up

The setup happens on mobile via QR code scan from the desktop interface. Here's the flow:

1. On desktop, go to gemini.google.com and click Add Files > More uploads > Avatar
2. Scan the QR code with your phone or tablet
3. Record your face and voice following the on-screen instructions (camera and microphone access required)
4. Return to desktop and click Use Avatar

Once set up, using your avatar in any prompt is as simple as typing @ and selecting your username. Example prompts from the official docs:

• Create a video of @[username] singing with an orchestra.
• Write a story where @[username] is the main character, facing a dragon.

Avatars in images and video

The avatar feature connects to two separate surfaces. On the image side, it builds on the Personal Intelligence system Google has been rolling out this year. AI images can be created using Gemini's understanding of your likes and interests, without those having to be explicitly noted in the prompt. This works because Gemini already has context of your data through Google account connections, such as Gmail and Google Photos.

On the video side, the avatar feeds directly into Google Vids. With new personal avatars in Google Vids, you can create a digital avatar that looks and sounds like you by uploading a selfie and a short voice recording. From there, type what you want to say and your avatar will deliver the message, no recording required. This is particularly useful for async video updates, training content, or personalized messages at scale.

Every generated clip includes an invisible SynthID digital watermark, allowing people to verify that a video was created with AI.

What it's good at, and where it falls short

Nano Banana's image generation has clear strengths worth knowing:

• Subject consistency: it can maintain character resemblance of up to five characters and the fidelity of up to ten objects in a single workflow.
• Accurate text inside generated images has been an industry failure mode since the original Stable Diffusion era. Nano Banana Pro is the first model where adding text like "Sale" in bold white on a product reliably produces readable text rather than decorative gibberish.
• Precise instruction following: the model adheres more strictly to complex requests, capturing specific nuances so the image you get is the image you asked for.

But it's not the best at everything. In independent user testing, 78% of participants preferred Imagen 4 Ultra for portrait photography (skin texture, eye detail), and 73% chose it for product shots. But 54% preferred Nano Banana Pro for stylized and creative output. If photographic realism is the goal, Imagen 4 Ultra still wins.

Availability and cost

To create an avatar, you must be 18 or over and signed in with a personal Google Account with a Google AI plan. Avatars are currently not available in the EEA, Switzerland, or the United Kingdom, and are currently only supported in English.

On the image generation side, the broader personalization features have been opening up. Google announced that the Gemini app is now offering its personalized Nano Banana-powered image generation feature to a broader audience, with all eligible users in the U.S. able to access it for free, a service previously only available to Plus, Pro, and Ultra subscribers. Avatar-based video creation in Google Vids, however, remains gated behind Google AI Pro and Ultra tiers.

The avatar feature is a meaningful quality-of-life upgrade for anyone already using Gemini for creative work. The one-time setup removes the biggest source of friction in personalized AI image generation, and the connection to Google Vids opens up a genuinely new use case: producing talking-head video content without ever turning on a camera.