Google Profile picture
Jun 24, 2025 6 tweets 4 min read Read on X
Sometimes the best ideas start with a sketch. ✍️

Here are 6 quick demos we vibe coded with simple drawings and a little help from Gemini 2.5 Pro. Try it yourself by going to gemini.google, select 2.5 Pro, tap Canvas, upload an image of your sketch, and ask, “Can you code this app?”

First up: recreate something nostalgic.

Prompt: create this app with HTML, CSS and javascriptA user uploads a hand-drawn sketch of a bouncing DVD illustration and asks Gemini to create an app with HTML, CSS, and Javascript.
Play interior designer before you move your furniture.

Prompt: Can you create a 3D representation of the space so I can experiment with the layout? A user uploads a hand-drawn floor plan of a room and asks Gemini to create a 3D representation to experiment with the layout.
Avoid having to do math at the end of brunch ever again.

Prompt: Can you code this app? A user uploads a hand-drawn sketch of a “Split Bill Calculator” app and asks Gemini to create a functional version.
Organize your weekly to-do list without taking up your whole Sunday.

Prompt: Can you code this app? A user uploads a drawing of a personal planner and asks Gemini to create an interactive dashboard for tracking weekly goals and habits.
Take the hassle out of choosing whether tonight is taco night, pizza night or a “it’s time for sushi takeout” night.

Prompt: Can you code this app? A user sketches a design for a “What Should I Eat?” app and asks Gemini to build a tool based on the drawing.
Map out your hiking routes more efficiently, without wasting your vacation time.

Prompt: I want you to code this web app for all the best hikes in Japan for me. Use Leaflet.JS for the interactive map. I want a sleek, minimal, dark mode interface using only black and white. The output should be one self contained HTML file.A user uploads a hand-drawn wireframe of a web app and asks Gemini to code an interactive map of the best hikes in Japan with a minimal, dark-mode interface.

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Google

Google Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @Google

Jan 14
Today, we’re introducing Personal Intelligence.

With your permission, Gemini can now securely connect information from Google apps like @Gmail, @GooglePhotos, Search and @YouTube history with a single tap to make Gemini uniquely helpful & personalized to *you* ✨

This feature is launching in beta today in the @GeminiApp.

See Personal Intelligence in action 🧵 ↓
1/ Reasoning across sources: Ever need to buy parts for your car but don't have the info handy?

Ask Gemini to “Recommend tires for my car.”

By referencing connected apps like @Gmail and Photos, it can understand your car’s make and model, and even the types of trips you take, to give recommendations of tires and info like your license plate number to make your visit to the auto shop go more smoothly.
2/ Personalized planning: Move past the generic "Top 10" travel lists.

Ask Gemini to “Recommend some hidden gems or activities I might enjoy in Chicago."

By connecting the dots between your travel dates in @Gmail and your love for nature photography in @GooglePhotos, Gemini can find spots tailored just for you — like the Garfield Park Conservatory.
Read 8 tweets
Dec 31, 2025
It’s been a huge year for our image generation and editing model Nano Banana, starting with its debut in August as the top-rated image editing model in the world. Then in November, we released Nano Banana Pro. Built on Gemini 3 Pro, Nano Banana Pro uses Gemini’s state-of-the-art reasoning and real-world knowledge to visualize information better than ever before.

Amid all this momentum, it’s been incredibly fun to see the creative ways you’re actually using Nano Banana. Here are some of the most fun Nano Banana trends we’ve seen this year — which one’s your favorite? 👀🍌
1/ General photo edits

Prompt: Turn this into a night scene, lit by the moon, with dramatic shadows and moody overall lighting. A day-to-night transformation of a photo of a person walking through a red rock canyon under a full moon.
2/ Figurines

Prompt: Create a realistic-looking small 3D model of this dog. Place the model on a desk next to birthday packaging that makes it look like someone unwrapped the model as a gift. A small, lifelike 3D model of a scruffy terrier-mix dog. The figurine sits on a wooden surface surrounded by red checkered tissue paper and an open cardboard gift box.
Read 14 tweets
May 20, 2025
AI Mode is Search transformed with Gemini 2.5 at the core. It’s our most powerful AI search, with more advanced reasoning and multimodality, and the ability to go deeper through follow-up questions and helpful links to the web.

Here’s a peek at what’s coming soon to AI Mode:
🧵
📫 Personal Context

This summer, AI Mode in Labs will be able to give you personalized suggestions based on your past searches. You’ll also be able to opt in to connect other Google apps, starting with Gmail. So for example, if you usually search for and book restaurant patios, it’ll learn that you prefer outdoor seating.

It’ll be under your control, and you can choose to connect or disconnect at any time.
📖 Deep Search

We’re introducing Deep Search in AI Mode in Labs so you can dive deeper on your research questions. Deep Search can issue hundreds of searches on your behalf, reason across all those disparate pieces of information, and create an expert-level, fully-cited report for you — in just minutes.
Read 7 tweets
Dec 23, 2024
Play it back. Here’s a recap of (most of) our AI launches this December. Here we go ⏪
🪩 Gemini 2.0 dropped, so it’s time to ring in the agentic era — here’s your cheat sheet for our most capable model yet. A graphic explaining that Gemini 2.0 has enhanced performance, more multimodality and native tool use. It also mentions that developers can start building with an experimental version of 2.0 Flash in the Gemini API in AI Studio and Vertex AI; Multimodal Live API lets you create interactive experiences that respond in real-time to text, audio and video input; and Gemini 2.0 Flash Thinking is a new experimental model that explicitly shows its thoughts. The text is blue and white on a black background.
You can now access Gemini 2.0 Flash Experimental in Gemini, your AI assistant. Plus, we introduced a bevy of updates for Gemini Advanced users: Text is white on a dark grey background, reading: New features for Gemini Advanced users. Features mentioned include Deep Research and gemini-exp-1206, and includes the update that you can now streamline your workflows by uploading your code repository directly from your device.
Read 12 tweets
Dec 16, 2024
📣 Today we’re making updates to our video and image generation models, with Veo 2 and Imagen 3, plus our newest experiment in gen AI, Whisk.

Learn more → goo.gle/3ZTcRcDThree different AI generated images in front of an abstract background
Veo 2, our state-of-the-art video generation model, has:
- A better understanding of real-world physics & nuances of movement
- The ability to understand language of cinematography, like lens type & effects
- Resolution up to 4K
Imagen 3, our highest quality image generation model, is now even better with:
- Brighter, better composed images
- More diverse art styles w/ greater accuracy
- Richer details and textures

Imagen 3 updates are starting to roll out to 100 countries → goo.gle/3DknSuHA person in a red cape looks over a galaxy of sorts, complete with constellations, shooting stars, rock formations and planets.
A close-up, macro photography stock photo of a strawberry intricately sculpted into the shape of a hummingbird in mid-flight, its wings a blur as it sips nectar from a vibrant, tubular flower. The backdrop features a lush, colorful garden with a soft, bokeh effect, creating a dreamlike atmosphere.
A foggy 1940s European train station at dawn, framed by intricate wrought-iron arches and misted glass windows. Steam rises from the tracks, blending with dense fog. Two lovers stand in an emotional embrace near the train, backlit by the warm, amber glow of dim lanterns. The departing train is partially visible, its red tail lights fading into the mist. The woman wears a faded red coat and clutches a small leather diary, while the man is dressed in a weathered soldier’s uniform. Dust motes float in the air, illuminated by the soft golden backlight. The atmosphere is melancholic and timeless...
A close-up shot captures a winter wonderland scene – soft snowflakes fall on a snow-covered forest floor.  Behind a frosted pine branch, a red squirrel sits, its bright orange fur a splash of color against the white. It holds a small hazelnut. As it enjoys its meal, it seems oblivious to the falling snow.
Read 5 tweets
Mar 31, 2022
April 2nd is International Fact Checking Day and we’re committed to help you spot misinformation online.

Google offers a range of tools and tips to help you make sense of information online ↓ The illustration has a magnifying glass on the righthand sid
Search makes it easy for you to evaluate results.

Tapping the three dots next to a Search result can help you dig deeper and learn more about its source. bit.ly/3LtEWx8 The illustration shows a smartphone with the Google Search i
Sometimes interest in a topic travels faster than the facts.

When information is rapidly changing, Search will alert you with helpful tips — and remind you that you can come back later when there's more information available. This illustration shows a smartphone on the right with the G
Read 4 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(