Revolutionize Your Instructions: Discover Google Gemini’s Innovative Drawing Feature!

Google continues to enhance Gemini to establish it as the preferred AI among users. With the introduction of Gemini 3 Flash, the tech giant has unveiled two major updates: a novel method of issuing commands to Nano Banana and the expansion of SynthID verification to videos. Here’s how you can make the most of these features.

Ever since the release of Nano Banana, Google has hit the jackpot: this AI image generation and editing tool from the Mountain View company has been quickly embraced by users who praise its effectiveness and the high quality of its output.

The tech giant has eagerly capitalized on the excitement surrounding its AI integrated within Gemini, incorporating it extensively: Nano Banana is set to soon feature in Google Search, could appear in the Chrome search bar, and has already been integrated into Adobe Photoshop. However, Google is far from resting on its laurels.

Gemini: Forget prompts, you can now draw your edits in Nano Banana, and there’s more

The Mountain View firm announced on the X (formerly Twitter) account @GeminiApp that Gemini has introduced a “brand new way to give instructions” to Nano Banana. You no longer have to struggle with crafting a detailed prompt in the input field: “You can now specify exactly where and how to apply your edits by drawing or annotating directly on your images within the app,” the post clarifies. The process is a breeze, simply:

• Open the Gemini app
• Select Create an Image
• Import the image you want to edit
• Tap on it
• Draw your instructions using the Sketch tool

• Or annotate them with the Text tool
• Press OK
• Then send

If the result doesn’t entirely meet your expectations, you can still refine your request with a prompt. This new feature is available on Android, iOS, and the web.

And that’s not the only new feature that was announced with the launch of Gemini 3 Flash. Also on X, Google mentioned that it is now possible to verify whether a video has been generated (or modified) by Google’s AI with Gemini. The Mountain View firm has indeed extended SynthID verification to videos: simply upload a media file and Gemini will inform you if the audio or video contains the watermark, and more importantly, which specific time segments are affected. For example: “SynthID detected in the audio between 10 and 20 seconds. No SynthID detected in the images.“