bytedance/seedream/v5/pro/layerize
Optional instructions describing which elements to separate. When empty, the model automatically separates the major elements. Normalized `<bbox>left top right bottom</bbox>` tags may be used for precise coordinate targeting.
URL of the image to decompose into a base image and independently editable layers. The image must contain between 512x512 and 6000x6000 total pixels, have an aspect ratio between 1/16 and 16, and be no larger than 30 MB.
Run the model to see the result here.