Free · 7 min read

Gemini for designers: what it can do and how to use it

How designers can use Google Gemini: what the free plan includes, how to review layouts, build a Gem for your project, generate images and keep private work private.

  • What free Gemini gives you and what needs a subscription
  • How to build your own Gem: an assistant that remembers your project's rules
  • What Google's reviewers see and how to stop saving your chats
Share your Gem
  • Free
  • 1,504 members
  • Join in 1 click

5 steps to make Gemini a real design tool

  1. 1

    Step 1

    Sign in and see what the free plan gives you

  2. 2

    Step 2

    Upload references and layouts for review

  3. 3

    Step 3

    Create a Gem for your project

  4. 4

    Step 4

    Generate and edit images

  5. 5

    Step 5

    Use Canvas and Deep Research for a case study

1,504
community members
8,915
messages with questions since July 2024
9
design games since September 2024
759
people wrote in the chat

This guide is for you if you are

  • Learning design

    You have a Google account and want to see how Gemini helps with design, not just search.

  • Building learning case studies

    You need to break down references, gather research and quickly sketch visuals for a presentation.

  • Already tried ChatGPT

    You're wondering whether another AI tool is worth opening and how it differs.

In short

  • The Gemini web app is available in Ukraine and supports Ukrainian; in the mobile app, "Hey Google" voice commands and some actions don't work in Ukrainian.
  • The free plan includes image generation and editing, Deep Research, Canvas and Gems; video generation in the Gemini app needs a Google AI plan.
  • Signed out, you only get text prompts: images, Gems and file uploads need a Google account.
  • A Gem is a saved set of instructions for one task: role, task, context and answer format, plus your project files.
  • Google's reviewers read a subset of chats, so keep confidential work out, or switch off Keep Activity or use a temporary chat.

5 steps to make Gemini a real design tool

  1. 1

    Step 1

    Sign in and see what the free plan gives you

    Open gemini.google.com in Chrome, Safari, Firefox, Opera or Edge and sign in with a personal Google account. Signed out, Gemini only answers text prompts; image generation, Gems and file uploads need an account. The free plan currently lists:

    • image generation and editing;
    • Deep Research: a report built from many sources;
    • Canvas: a shared editor for docs, slides and code;
    • Gems: your own assistants with instructions;
    • Gemini Live and Google Flow, a video studio with free daily credits.

    💡 Google doesn't publish one number for free limits: Gemini tells you when you reach them. Paid Google AI plans raise limits and add features such as video generation.

  2. 2

    Step 2

    Upload references and layouts for review

    Gemini reads images, PDFs, spreadsheets and video. You can add up to 10 files per prompt: up to 100 MB each, videos up to 2 GB, and up to 5 minutes of video in total on the free plan. Click Add files next to the input box. For a designer, it's a quick way to break down other people's decisions or your own layout:

    • "Here are 5 screenshots of competitors' onboarding. Compare them in a table: number of steps, what they ask for, how they explain the benefit";
    • "Here's a screen recording of my prototype. Where might a user get stuck?";
    • "Here's the brand guidelines PDF. List the button and color rules that apply to the mobile app".

    💡 We covered how to set tasks for brief analysis and interface copy in ChatGPT for designers: the same prompts work in Gemini.

    Swap Gems and prompts

    People in the community share how they set up AI assistants and honestly show what didn't work. Come in, it's free.

    Share your Gem

    Free. 1,504 designers are already in the community.

  3. 3

    Step 3

    Create a Gem for your project

    A Gem is a saved assistant with your instructions, so you don't explain the context every time. On the web, open Explore Gems → New Gem, name it and write instructions. Google suggests four parts:

    • Persona: "You are an experienced product designer who reviews layouts";
    • Task: "Critique screens for hierarchy, readability and clear actions";
    • Context: "The product is a barber booking app; users book from their phones";
    • Format: "First the 3 main problems, then a table of minor notes";
    • under Knowledge, add files: the brief, guidelines, interview notes.

    💡 Not sure where to start? Write a sentence or two about the goal and click "Use Gemini to re-write instructions": Gemini expands them and you edit. Click Save before leaving: the preview doesn't save the Gem.

  4. 4

    Step 4

    Generate and edit images

    In the sidebar, choose Images and describe the picture. According to Google's help page, images in Gemini are currently made by the Nano Banana 2 model: it keeps a character's look across images, edits specific parts and renders text in the image. Without a paid plan, images download at 1K; with a Google AI plan, at 2K. Good to know:

    • Google suggests starting with words like draw, generate or create, naming the style (photorealistic, watercolor, cartoon illustration) and describing the subject, action and background in detail;
    • to edit an image, open it in Library and click Chat under it, or simply upload your own image to the chat;
    • you can generate images from age 13, but editing is 18+ only;
    • Google specifically warns not to violate other people's copyright or privacy.

    💡 More on how to structure image prompts in How to write prompts for AI image generation.

    Gemini missing the point? Ask the community how they set the task →
  5. 5

    Step 5

    Use Canvas and Deep Research for a case study

    Two tools that are especially useful for a learning case study. Canvas opens via Add files → Canvas: Gemini creates a doc, slides or even a simple app, and you edit the text directly or select a part and ask to change just that (Select & ask). Deep Research drafts a research plan for your topic, lets you edit it and returns a sourced report in 5–10 minutes. Ideas to start with:

    • "In Canvas, outline a case study presentation: problem, research, solution, result, one slide each";
    • "Deep Research: how people choose apps for booking appointments, and the typical complaints in reviews";
    • "Here's the report. Pick 5 hypotheses for my learning project and mark which ones need interviews to test".

    💡 Gemini can make mistakes, and a Deep Research report is a collection of other people's sources, not your research. Check the links, and in your case study be honest about where you had real interviews and where you had desk research with AI.

You're not alone with these questions

We counted what people ask about most in our community. AI tools are the fourth most popular topic, after learning, portfolios and Figma.

You're not alone with these questions
Learning and courses938
Portfolio and case studies705
Figma647
AI tools380
Jobs and vacancies314
UX research131

Messages by topic in Spaceberry Community, July 2024 — November 2026. Keyword search.

Practice with a deadline and live feedback

The best teacher is a task with a deadline that other people see. That's why the community regularly runs design games: the same brief for everyone, a deadline and a vote.

  • Design game · January 2026

    NAOMA website redesign

    The academy's home page through the eyes of an applicant, a student and a teacher. Three finalists; the community chose the winner.

  • AI challenge · May 2025

    A landing page made by AI

    Logo, copy and visuals made only with AI tools. Four entries, an anonymous vote, and participants shared their prompts.

  • Workshop · April 2026

    Figmosha: AI in Figma

    The tool's author showed how to generate interfaces in Figma and analyze a design system.

Share your Gem

Free. 1,504 designers are already in the community.

How to join: 1 minute

  1. 1

    Tap the button

    Telegram opens with the Spaceberry community.

  2. 2

    Join

    It's free: all you need is a Telegram account.

  3. 3

    Introduce yourself

    Say where you're starting from and ask your first question.

Questions and answers

Didn't find your answer? Ask it in the community.

Does Gemini work in Ukrainian and in Ukraine?

Yes. Ukraine is on the list of countries where the Gemini web app is available, and Ukrainian is a supported language. You can chat in Ukrainian in the mobile app too, but according to Google's help page, "Hey Google" voice commands and some app actions don't support it.

Is Gemini free?

The basic plan is free with a Google account: it includes image generation and editing, Deep Research, Canvas and Gems, with usage limits. Paid Google AI plans raise the limits and add features, including video generation in the Gemini app. Prices depend on your country, so check the Gemini subscriptions page for current terms.

Who can see my Gemini chats?

Google's reviewers read a subset of chats to improve the service, and reviewed chats are kept for up to three years even if you delete your activity. To keep future chats out of review, switch off **Keep Activity** or use a **temporary chat**: it doesn't appear in your history, is kept for 72 hours and isn't used to train models. Better not to upload NDA work or personal data at all.

Gemini or ChatGPT: which should a designer pick?

Both handle copy, image analysis and image generation, so either is enough for learning. Gemini is handy if you already work in Google Docs and Drive: you can export results to Docs. Try the same task in both and keep the one whose answers you rewrite less. How to set tasks for ChatGPT: [ChatGPT for designers](/en/guides/chatgpt-for-designers).

Is the Spaceberry community paid?

No. Spaceberry Community is a free Telegram community supported by Spaceberry Foundation, a non-profit organization. All you need to join is a Telegram account. Inside are 1,504 designers who discuss each other's work, plus regular design games: the same brief for everyone, a deadline and a community vote. Conversations are in Ukrainian.

Try Gemini on a real task

Join 1,504 designers who learn, share their work and play design games. Show what you made and see how others set tasks for AI. The community talks in Ukrainian.

Show your result
  • Free
  • 1,504 members
  • Join in 1 click

Updated · Spaceberry Foundation

Bohdan Ostafiiv

Reviewed by: Bohdan Ostafiiv, COO at Spaceberry Studio

7+ years designing interfaces for web and mobile apps, 150+ projects. Mentors the Spaceberry design team.

LinkedInBehanceDribbble

Sources: