Create & edit images in Google Flow

You can create and edit images directly within your Google Flow projects to use as stand-alone assets or as ingredients for your videos.

Create an image in Google Flow

Create images with the Google Flow Agent

  1. On your device, go to Google Flow.
  2. Click an existing project.
  3. In the prompt box, turn on Agent.
  4. Add a text prompt that describes the image you want to create in detail.
    • You can ask the Agent to create multiple variations of an image at once.
    • For example: “Give me 20 variations of this image with different lighting.”
  5. Optional: To add ingredients to your prompt, drag media into the prompt box from your device or project.
  6. Click Generate .
    • Based on your inputs, the Agent routes your request to the best image model.

Create an image with the standard Google Flow prompt box

  1. On your device, go to Google Flow.
  2. Click an existing project.
  3. In the prompt box, click the model name.
    • By default, Google Flow sets the model to Nano Banana Pro.
  4. Click Image.
  5. Select your image preferences:
  6. Add a text prompt that describes the image you want to create in detail.
  7. Optional: Add ingredients to your prompt.
  8. Click Generate .

Learn how to find your images in Google Flow.

Edit an image in Google Flow

When you edit an image in Google Flow, you don’t lose the original image. In the History panel, you can find all previous versions of the image and the prompts you used to generate them.

Edit an image with the Google Flow Agent

  1. On your device, go to Google Flow.
  2. Click an existing project.
  3. In the prompt box, turn on Agent.
  4. Drag the images you want to edit into the prompt box, or select multiple images to edit them all at the same time.
  5. Add a text prompt that describes what you want to change.
    • For example: "Make these black and white."
  6. Click Generate .
    • Edits are automatically saved to the asset's stack.

Crop an image

  1. On your device, go to Google Flow.
  2. In an existing project, click the image you want to edit.
  3. On the left, click Crop .
  4. Select how you'd like to crop the image.
  5. Click Crop.

Select & edit part of an image

You can use the Nano Banana model to make iterative edits to your images. For example, you can add or remove objects from your image.

  1. On your device, go to Google Flow.
  2. In an existing project, click the image you want to edit.
  3. On the left, click Select .
  4. On the image, select what you want to edit.
  5. At the bottom, in the prompt box, describe what you want to change.
    • Tip: You can enter a prompt to add or remove an object from the image. 
  6. Click Generate .

Draw on an image

  1. On your device, go to Google Flow.
  2. In an existing project, click the image you want to edit.
  3. On the left, click Draw .
    • To add text to your image: Click Text .
    • To draw a box on your image: Click Rectangle .
  4. Draw on your image.

Add references to your prompt

Add images to your prompt

  1. On your device, go to Google Flow.
  2. In an existing project, hover over the image.
  3. Click More and then Add to Prompt.

Save images to your project

To add a previous version of an edited image in your prompt, save that version to your project first.

  1. On your device, go to Google Flow.
  2. In an existing project, click the image.
  3. On the right, in the History panel, hover over the version you want.
  4. Click Save to Project .

Add characters to your prompt

  1. On your device, go to Google Flow.
  2. Click an existing project or start a new one.
  3. In the prompt box, type @ followed by your character's name.
  4. Describe how your character should be used as a reference.
    • For example: @CaptainZoro walking through a futuristic city. 

Tip: Learn how to create a character in Google Flow.

Search
Clear search
Close search
Main menu
5028932077204510808
true
Search Help Center
false
true
true
true
false
false
false
false
false