Generating Images

When you open the Image Generation tab, a screen like this is displayed. To generate images, you first need to select the model you want to use for image generation.

To select a model, click or tap the model switch button in the top right corner. This will display a list of models on the currently selected Ollama server, and you can select the model you want to use (to switch the selected server, please refer to the Server Tab documentation).

Once a model is selected, you can enter a prompt. Type the text you want to send to the image model and click or tap the Send button.
To insert a line break on macOS, press ⇧ (Shift) + ↩︎ (Return) simultaneously.

When you send a prompt, an image generation request is sent to the Ollama server, and the model loading process will begin if necessary.
Loading may take time depending on the model type and the type of storage where the model is saved on the Ollama server.

Tip
The API timeout is set to 30 seconds by default, so a timeout error may occur if model loading takes a long time.
If you know that model loading will take time, I recommend increasing the API timeout duration in Settings or setting it to unlimited.
For instructions on how to set the API timeout duration, please refer to the Settings documentation.

After a while, the image generation will begin. While the image is being generated, the progress for each step will be displayed.

Once the image generation is fully completed, you can perform operations on the image. The possible operations are as follows:

• Your Prompt
  • Copy
    • You can copy the prompt as Markdown-formatted text.
  • Edit
    • You can edit the sent prompt and resend it. Only the last sent prompt can be edited.
• Generated Images
  • Switch to Previous Revision
    • You can switch to the revision before the regeneration. This is displayed only if there are two or more revisions.
  • Switch to Next Revision
    • You can switch from the previous revision to the next revision. This is displayed only if there are two or more revisions.
  • Retry
    • You can regenerate the image. Only the last image can be regenerated.
  • Copy
    • You can copy the image.
  • Save
    • You can save the generated image to your photo library or as a file.
  • Share
    • You can share the generated image.

Previewing Generated Images

Clicking or tapping a generated image allows you to preview the image in an enlarged view.

The following operations are available on the preview screen:

• Zoom In/Out
  • All Platforms
    • Double-click or double-tap the image to zoom in (2x) or zoom out to the default view.
    • Press ⌘ (Command) + = to zoom in, ⌘ (Command) + - to zoom out, and ⌘ (Command) + 0 for the default view.
    • Pinch out on the trackpad to zoom in, and pinch in to zoom out.
  • macOS
    • Hold ^ (Control) and left-click, or right-click and drag upward to zoom in, or drag downward to zoom out.
  • iOS / iPadOS / visionOS
    • Long-press the image for 0.5 seconds, then swipe up to zoom in or swipe down to zoom out.
      • On devices equipped with the Taptic Engine, haptic feedback will occur after a 0.5-second long-press, letting you know through touch that you have entered zoom mode.
    • Pinch out with two fingers or both hands (visionOS) to zoom in, and pinch in to zoom out.
• Move Preview
  • All Platforms
    • Click or tap and drag the image.
    • Scroll with a mouse or trackpad.
• Close Preview
  • All Platforms
    • Click or tap the image or the background.
    • Press the Esc key.

Starting a New Image Generation

To clear the image generation history and start a new generation, click the New Image Generation button in the top right corner or press ⌥ (Option) + ⌘ (Command) + R simultaneously.

Changing Image Generation Settings

By opening the Inspector, you can customize the image generation settings.
To open the Inspector, click or tap the sidebar toggle button in the top right corner.

From the Inspector, you can customize the following settings:

• Image Generation Settings
  • Stream Response
    • Toggles whether to receive the image generation progress continuously. If turned off, you will not receive a response until the final result is returned, so I recommend setting the API timeout to unlimited. For instructions on how to set the API timeout duration, please refer to the Settings documentation.
  • Keep Alive
    • Select how long the model stays loaded in the server's memory.
  • Width
    • Specifies the width of the image you want to generate.
  • Height
    • Specifies the height of the image you want to generate.
  • Steps
    • Specifies the number of image generation steps. Increasing the number of steps increases generation time but can improve detail.
  • Seed
    • You can specify a seed value to achieve reproducible generation.
• Custom Settings
  • Custom Width
    • Enter the desired image width as a number to override the above setting and manually specify the size.
  • Custom Height
    • Enter the desired image height as a number to override the above setting and manually specify the size.
  • Custom Steps
    • Enter the number of image generation steps as a number to override the above setting and manually specify the size.

The settings configured here will be reflected from the next prompt you send onward.