midjourney_transform
Modify existing Midjourney images by upscaling, creating variations, zooming, or panning to refine generated artwork.
Instructions
Transform an existing Midjourney image with various operations.
This allows you to upscale, create variations, zoom, or pan existing images
generated by Midjourney.
Use this when:
- You want to upscale one of the 4 images from a generation
- You want to create variations of a specific image
- You want to zoom out or pan an image
- You want to regenerate with the same prompt
Workflow example:
1. Generate with midjourney_imagine -> get image_id
2. Upscale favorite: midjourney_transform(image_id, "upscale2")
3. Further upscale: midjourney_transform(new_image_id, "upscale_4x")
Returns:
Task ID and transformed image information.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| image_id | Yes | ID of the image to transform. This is the 'image_id' field from a previous generation result. | |
| action | Yes | Transformation action to perform. Options include: - upscale1/2/3/4: Upscale one of the 4 images (top-left=1, top-right=2, bottom-left=3, bottom-right=4) - upscale_2x/4x: Further upscale an already upscaled image by 2x or 4x - variation1/2/3/4: Create variations of one of the 4 images - variation_subtle/strong: Create subtle or strong variations after upscaling - reroll: Regenerate all 4 images with the same prompt - zoom_out_2x/1_5x: Zoom out the image by 2x or 1.5x - pan_left/right/up/down: Pan the image in a direction | |
| prompt | No | Optional prompt for the transformation. Used with variation_region action. | |
| mask | No | Base64-encoded mask image for variation_region action. White areas indicate regions to regenerate. | |
| mode | No | Generation mode for the transformation. | fast |