How to generate AI images
Create classroom-ready images using Monsha's Image Generator tool.
Monsha's Image Generator helps you create visuals for a wide range of classroom uses. You can generate labelled diagrams for science, timelines for history, character illustrations for literature, classroom posters for any subject, or anything else really.
These images can be used in your worksheets, presentations, assessments, or as standalone learning aids, among other use cases.
Follow the steps:
Step 1: Open the Image Generator
Go to app.monsha.ai and sign in or sign up with your email.
From the tools list, select Image Generator to begin.
Step 2: Add your requirements and sources
Type your prompt, topic, or instructions in the Describe your requirement... textarea. A short description works fine — e.g., "Photosynthesis diagram" or "Ancient Egyptian pyramids cross-section".
Click the Attach dropdown below the textarea to add a source. Add any combination of:
Video — paste a YouTube link and Monsha will analyse the transcript.
File — upload documents, slides, spreadsheets, or images.
Website — link to articles, image URLs, blog posts, or any web page.
Text — paste a passage directly.
Monsha Resource — pull from worksheets, slides, or other Monsha resources you've already created.
The more context you give, the better and more relevant your image output.
Click History if you want to reuse a past prompt. The Prompt History panel lists your previous Image Generator prompts — click any one to load it back into the textarea.
Set the Grade and Language for your image:
Grade opens a three-column picker. Pick your education system first (United States / Canada, United Kingdom, Australia, India / South Asia, IB, Cambridge, Age-Based, or University / Tertiary), then a sub-level, then the specific grade.
Language lets you choose the language for any text in or around the image. Monsha supports a long list of languages with native names alongside the English names.
Step 3: Configure image attributes (optional)
Click Configure Resource to open the Image Generator Configuration modal and tell Monsha exactly what you want.
You can skip this step, but defining these attributes helps the AI understand the specific context, style, and purpose of your image. The clearer your preferences, the less you'll need to revise the output.
The modal asks you ten questions:
Field | What it controls |
Where will you use this image? | The use case — Assessment, Bulletin Board, Classroom Poster, Homework, Interactive Activity, Lesson Slide, Presentation, Worksheet, or + Other. Multi-select. |
What type of image? | The format — Diagram, Illustration, Infographic, Map, Portrait, Scene, or + Other. |
What is the main subject? | The central thing in the image — e.g., a cell, a continent, a character. |
What is the subject doing? | The action or state — e.g., dividing, migrating, reading. |
Choose artistic style | Cartoon, watercolour, realistic, line art, and so on. |
Set the mood/tone | Fun, educational, inspirational, serious, etc. |
Select background type | Blank, nature, classroom, abstract, and so on. |
Choose color scheme | Vibrant, pastel, monochrome, high contrast, etc. |
Choose composition style | How the elements are arranged — close-up, wide, grid, side-by-side, etc. |
Set level of detail | How dense and intricate the image should be — minimal, moderate, highly detailed. |
Click Save Configuration when you're done. The settings stick to this resource until you change them.
If you want to layer on more structure — like tying the image to a specific course, learning standard, or framework — click More Options next to Configure Resource:
Attach to course — link the image to one of your existing Monsha courses.
Assign standards — tag the image against curriculum standards.
Adapt to framework → — match the image to a learning framework. Submenu: Depth of Knowledge (DOK) Levels, Lexile Reading Levels, Bloom's Taxonomy.
Step 4: Generate your image
Click Generate. If you want Monsha to pull in fresh information from the web while generating, turn on the Web search toggle to the right of the Generate button first — it lets Monsha search the internet to help generate content.
Monsha will produce:
The image itself, rendered inside a content card.
Alt text for accessibility, attached to the image.
A short description paragraph for context, shown below the image.
What you can do after generating
Once Monsha finishes, the resource page splits into two cards: a title card at the top (with the resource name, metadata chips, and Share/More controls) and a content card below it (with the image, description, and Edit/Export/More controls). A chat bar sits fixed at the bottom of the page.
From here, you can:
Chat with it. Type a follow-up prompt into the Reply here to keep going bar to tweak colours, annotations, composition, or style. Hit the send arrow or press Enter.
Use Quick prompts. Click Quick prompts in the chat bar to pull up ready-made instructions: Make it engaging, Create another variation, Focus more on..., and Change attributes → (Image Type, Style, Color Palette, Detail, Layout). These save you from writing every revision prompt by hand.
Turn on Web search. The globe icon on the right of the chat bar toggles web search for follow-up prompts — useful when you need fresh references mid-conversation.
Edit the title or description. Click Edit in the content card to open a rich-text editor for the resource title and description. The toolbar covers Insert, Bold / Italic / Underline / Strikethrough, alignment, lists, links, tables, and inline images. Click Save when done, or Cancel to discard changes.
Export. Click Export in the content card to open the Export Resource modal. Tiles: Download as PNG, Download as JPG, Download as WEBP, Export to Google Docs, Share to Google Classroom, Download as DOCX, Download as PDF.
Create more resources from this image. Open More on the content card and choose Create more resources based on this output to spin up worksheets, slide decks, study materials, or anything else from the same image and prompt.
Differentiate the resource. Open More on the content card and choose Differentiate to open the Differentiate Resource modal. Options: Translate, Adjust Grade Level, Adjust DOK Level, Adjust Lexile Reading Level, Adapt to Bloom's Taxonomy.
See the original prompt. Open More on the title card and choose See Prompt to view the prompt and configuration that produced this image. Create based on this lets you start a new resource from the same setup.
Share. Click Share on the title card. You can copy a shareable link (anyone with the link can view it without logging in), turn on Allow this resource to be publicly indexed and discoverable to let it show up in search, or share it via email to specific colleagues — paste one or more addresses, add a short message, and send.
Your images are always saved in your Monsha account for future access, editing, or reuse.