AI Watermark Center
Nano Banana research

Nano Banana Watermark

How Nano Banana and Nano Banana 2 document SynthID, Content Credentials (C2PA), and visible marks — and what AI Watermark Center can inspect locally.

Published
Last updated
Last verified
Review
Reviewed against primary sources

Does Nano Banana have a watermark? Official Google documentation says generated Nano Banana images — including Nano Banana 2 surfaces where documented — can carry imperceptible SynthID watermarking and, on some surfaces or model cards, Content Credentials (C2PA). That is not the same as a visible Gemini logo, and SynthID is not the same as C2PA. AI Watermark Center does not currently detect SynthID.

Relationship to Gemini image models

Nano Banana is Google’s Gemini image-generation family, not a single timeless model. Current official names include Nano Banana (Gemini 2.5 Flash Image, legacy), Nano Banana 2 Lite, Nano Banana 2, and Nano Banana Pro. Google’s 30 June 2026 developer post lists those names against Gemini 3.1 Flash Lite Image, Gemini 3.1 Flash Image, Gemini 3 Pro Image, and the legacy Gemini 2.5 Flash Image. Do not treat every historical Nano Banana file as using the same policy.

SynthID

Google states that all media generated by Google’s tools is embedded with SynthID, and Gemini API image-generation docs say all generated images include a SynthID watermark. DeepMind describes the image signal as added at creation and designed to survive some cropping, filters, and compression. Survival is not a guarantee after heavy edits. This site does not score watermark “strength.”

Visible marks by surface

Visible-mark behavior is a product-surface question. Gemini Apps Help currently documents an Apps-only visible-watermark setting; it explicitly does not apply to AI features in other Google products. Google AI Studio, the Gemini API, Search, and Ads are not assumed to inherit the Apps toggle. Documented Gemini Apps behavior is not automatically true of Google AI Studio, the Gemini API, Search, Ads, or other Google products. A November 2025 Nano Banana Pro post described a sparkle on free and Pro Gemini-app images and its removal for Ultra and AI Studio — that is chronology, not a live tier table.

Content Credentials where documented

Gemini Apps Help says Apps include C2PA metadata about origin for AI-created or edited media. Separately, the Gemini API model card for Nano Banana 2 Lite documents SynthID always on plus C2PA. That API model claim is not automatically copied onto every Nano Banana version or every consumer surface.

Public verification

Upload a supported original file (not a collage) in signed-in Gemini Apps and ask whether Google AI created or edited it. Gemini currently recognizes Google AI SynthID only. Google’s June 2026 Nano Banana 2 Lite post also mentions verification through Gemini in Chrome or Search. Those are Google products, not this site.

Official Google verification (opens in a new tab)

Inspect Content Credentials

What AI Watermark Center can do

  • Inspect embedded C2PA in JPEG, PNG, and WebP.
  • List ordinary metadata when parsers can read it.
  • Cannot detect SynthID, cannot inspect video, cannot recover remote credentials.

Sources

  1. SynthID — Google DeepMind

    Accessed August 16, 2026.

    SynthID modalities (image, video, audio, text). Gemini Apps can check Google AI media. A separate SynthID Detector portal remains an early-tester waitlist, not a general-availability consumer product, as of this access date.

  2. Verify AI-generated images, videos, and audio — Gemini Apps Help

    Accessed August 16, 2026.

    Gemini user-facing verification for image, video, and audio. SynthID identification is Google AI only; Content Credentials inspection is a separate layer.

  3. Manage watermark settings in Gemini Apps — Gemini Apps Help

    Accessed August 16, 2026.

    Current Gemini Apps visible-watermark toggle is Apps-only. India, South Korea, and Vietnam restrict the toggle to AI Ultra; work/school accounts cannot turn it off. The setting does not affect SynthID or Content Credentials.

  4. Nano Banana Pro: Gemini 3 Pro Image model from Google DeepMind — Google

    Published November 20, 2025. Accessed August 16, 2026.

    Historical 20 Nov 2025 launch post: all Google-tool media embedded with SynthID; Gemini-app image verification. Visible sparkle policy in this post is chronological, not a substitute for current Gemini Apps Help.

  5. Start building with Nano Banana 2 Lite and Gemini Omni Flash — Google

    Published June 30, 2026. Accessed August 16, 2026.

    Defines the current Nano Banana family (legacy, 2 Lite, 2, Pro) and states Nano Banana 2 Lite and Gemini Omni use SynthID. Mentions verification through the Gemini app, Gemini in Chrome, or Search.

  6. Nano Banana image generation — Google AI for Developers

    Accessed August 16, 2026.

    Nano Banana is four Gemini API models. All generated images include a SynthID watermark. Does not, by itself, document C2PA for every model.

  7. Gemini 3.1 Flash Lite Image — Google AI for Developers

    Accessed August 16, 2026.

    Nano Banana 2 Lite (gemini-3.1-flash-lite-image): SynthID always on plus C2PA watermarking. Scope is this API model card, not every Google consumer surface.

In this cluster