Feature availability
- This feature requires an eligible Google Workspace or Google AI plan. Learn how to get started with Google Workspace with Gemini.
- Google Workspace Experiments, which is a trusted tester program for personal accounts to try new AI features. Learn more about Workspace Experiments.
- This feature is currently available on desktop and in English only.
- If you don’t have access to personalization when using Help me create, your experience will look different. Learn how to generate an image with Gemini in Google Docs
- Learn where you can use Workspace Experiments features.
Generate an image with Gemini
You can ask Gemini to create images or infographics to support your content, directly within your document.
- On your computer, open a document in Google Docs.
- At the bottom bar
Write a prompt describing the image you want.
- To insert the image, select Accept.
Write a prompt describing the image you want.| If your goal is: | You should use a prompt like: |
| Generate professional infographics | "Visualize my document by creating an infographic summarizing key ideas and insert it at the top" |
| Add a visual timeline to a project | "Create a visual horizontal project timeline based on the dates in this document and insert it below the introduction." |
| Create a step-by-step process guide | "Generate a visual 4-step flowchart showing the onboarding process described in this text and place it in the 'Workflow' section." |
| Build a high-level Mind Map | "Visualize the main themes of this brainstorm as a mind map with a central node and radiating branches." |
Edit an image with Gemini
You can ask Gemini to edit your images or infographics.
- On your computer, open a document in Google Docs.
- Click on an image and select
on its bottom-left corner.
- In the bottom bar, describe how you want to change the image, for example: "Make the lighting darker." Or you can also select one of the suggestions.
- Optional. To find edit suggestions, click More
to select a prompt starter.
- Click
or enter.
- To insert the edits, select Accept
.
on its bottom-left corner.
to select a prompt starter.
or enter.
.| If your goal is: | You should: |
| Edit an object in an existing image | Select an image  click More Select "Swap [object] with…" Edit the prompt in the prompt box to something like: "Swap the arrow pointing up in the picture for a red arrow pointing down". |
| Implement the same edit into all images at once |
Select the images and write a prompt like: "Change the background to the corporate colors: blue and white." |
Give feedback on generated images
Google Workspace with Gemini constantly learns and may not be able to support your request.
If you get a suggestion that's inaccurate or makes you feel unsafe, you can submit feedback to let us know. Your feedback can be used to enhance AI-assisted Workspace features and expand Google efforts in AI.
Because feedback may be human readable, please do not submit data that contains personal, confidential, or sensitive information.
- On your computer, below the generated image, select Good suggestion
or Bad suggestion
.
- In the pop-up window, select if you want to share outputs along with your feedback. If you don't want to share it, you can uncheck it.
- If you select Bad suggestion
- To select the issue you found, select Next.
- Enter additional feedback.
- If you select Bad suggestion
- Click Submit.
or Bad suggestion 
.To provide general feedback on this feature, at the top, click Help
To report a legal issue, create a request.
Learn about Workspace Experiments feature suggestions
- Workspace Experiments feature suggestions don’t represent Google’s views, and should not be attributed to Google.
- Don’t rely on Workspace Experiments features as medical, legal, financial, or other professional advice.
- Workspace Experiments features may suggest inaccurate or inappropriate information. Your feedback makes Workspace Experiments more helpful and safe.
- Don’t include personal, confidential, or sensitive information in your prompts.
- Google uses Workspace Experiments data and metrics to provide, improve, and develop products, services, and machine learning technologies across Google.
- Your Workspace Experiments Data may also be read, rated, annotated, and reviewed by human reviewers. Importantly, where Google uses Google-selected input (as described in the Privacy Notice) to generate output, Google will aggregate and/or pseudonymize that content and resulting output before it is viewed by human reviewers, unless it is specifically provided as part of your feedback to Google.
- Generated images are for use only within Google Docs.
- Workspace Experiments generated images are designed to bring your imagination to life in Google Docs, and may not represent real-world situations.
Learn how Workspace Experiments data in Google Docs is collected
When you use “Generate an image” in Google Docs, Google uses and stores the following data:
- Prompts you enter or select
- Image styles you select
- Generated images
- Your feedback on generated images
To understand how this data is used, you can review the Google Workspace Experiments Privacy Notice and Terms for Personal Accounts.