Skip to main content
Edit Text detects all text regions in an image, lets you change what the text says, and regenerates the image with your new wording. The AI preserves the original fonts, colors, and layout so the edit looks natural. This is a direct canvas operation, so you do not need to send a prompt to the agent.
Using canvas tools directly gives you more control and uses significantly fewer credits than sending a prompt to the agent. For text changes, always use this tool instead of asking the agent.

​
How to edit text in an image

1

Select an image on the canvas

Open the canvas in the side panel and click the image that contains text you want to change. The image editing toolbar appears.
2

Click Text Edit

In the toolbar, click the Text Edit button. The AI scans the image and detects all text regions. This takes a few seconds.
Canvas toolbar with the Text Edit button highlighted
3

Review the detected text

Each detected text region appears as an editable field with its current wording and a bounding box overlay on the image showing where it is located.
Image with colored bounding boxes around each detected text region, with editable text fields displayed alongside
Review the detected regions to confirm the AI found all the text correctly.
4

Change the text you want to update

Click into any detected field and type the new text. You can edit one region or several at once. Leave fields unchanged if the text is fine as it is.
5

Click Apply

The AI regenerates the image with your updated text. The fonts, colors, positioning, and all non-text elements are preserved. A new image appears on the canvas with the changes applied.
Two canvas items side by side — the original image with old text and the edited image with new text, same styling preserved
Edit Text creates a new canvas item. It does not overwrite the original. You always keep both versions.

​
When to use this

  • Fixing typos or updating wording on marketing materials, social media graphics, or posters.
  • Translating text in an image to a different language.
  • Swapping placeholder text for final copy in mockups and designs.
  • Updating dates, names, or numbers on existing graphics without redesigning from scratch.

​
What you cannot do

  • You cannot add new text to an area where none exists. The tool only edits text that is already detected in the image.
  • You cannot change the font, font size, or color of the text yourself. The AI matches the original style automatically.
  • You cannot select which text regions to detect. The AI scans the entire image and finds all text.
  • You cannot edit text in a video frame. This tool works on images only.
If the AI does not detect all the text in your image, the text may be too small, blended into the background, or in a stylized font that is hard to read. Try Mark & Edit instead, where you can draw a rectangle around the text area and describe the change manually.

​
Next steps

Mark & Edit

Draw on specific areas and describe changes when text detection is not enough.

Remove Background

Strip the background from any image with one click.