ByteDanceSeedreamLayerSeparationNode - ComfyUI Built-in Node Documentation - ComfyUI

ByteDance Seedream 5.0 Pro Layer Separation decomposes an image into a background plate plus up to 16 transparent layers, each with its own stacking order, bounding box, name, and description. It returns the background, per-layer images with masks, placement boxes, and a ready-to-edit layer stack.

Inputs

Parameter	Description	Data Type	Required	Range
`image`	The image to separate. Exactly one image, at least 512x512 pixels, aspect ratio between 1:16 and 16:1. Inputs larger than about 4MP are downscaled before upload.	IMAGE	Yes	Single image
`prompt`	How to separate the image. Leave empty to auto-detect and separate all major elements. Describe elements in natural language to control the separation, or target exact regions with `<bbox>left top right bottom</bbox>` tags (0-1000 per-mille coordinates). Default: empty string.	STRING	Yes	Multiline text
`size`	Output resolution level. “auto” follows the input image size (clamped to the 1K-2K range). Default: “auto”.	STRING	Yes	”auto" "1K" "1.5K" "2K”
`seed`	Seed to use for generation. Default: 0.	INT	Yes	0 to 2147483647
`prompt_optimization`	Prompt-optimization mode: “standard” gives higher quality, “fast” shorter generation time. Default: “standard”.	STRING	No	”standard" "fast”
`watermark`	Whether to add an “AI generated” watermark to the images. Default: false.	BOOLEAN	No	false true
`crop_layers`	Geometry of the layers/masks batch outputs (layer_stack is unaffected and always tight). Full canvas: each layer on a base-sized canvas at its bounding-box position - recompose directly with ImageCompositeMasked. Minimal size: each layer cropped to its bounding box (padded to the largest layer for batching) - much smaller tensors; rebuild placement with Layers From Bounding Boxes using the bboxes output. Default: false (full canvas).	BOOLEAN	No	false (full canvas) true (minimal size)

Note: The input image must be a single image; batches are not supported. The image must be at least 512x512 pixels with an aspect ratio between 1:16 and 16:1.

Outputs

Output Name	Description	Data Type
`base_image`	The base image (background plate) the layers stack onto.	IMAGE
`base_mask`	Transparency of the base image (1 = transparent, LoadImage convention); currently always fully opaque.	MASK
`layers`	Transparent layers ordered bottom to top. Full canvas mode: placed on a black base-sized canvas at their bounding-box position. Minimal size mode: cropped to their bounding box, anchored top-left, padded to the largest layer.	IMAGE
`masks`	Per-layer transparency, index-aligned with the layers batch (1 = transparent, LoadImage convention). For ImageCompositeMasked-style compositing, add InvertMask first.	MASK
`bboxes`	One placement box per layer, index-aligned with the layers batch (feed both, plus masks, into Layers From Bounding Boxes to rebuild per-layer placement): `{x, y, width, height, metadata: {name, desc, z_index, native_size, content_rect, flags}}`. `content_rect = [left, top, width, height]` is the layer’s content region within its own frame; it lands on the canvas at the box position plus that offset.	BOUNDING_BOX
`layer_stack`	Ready-to-edit layer document for Create Layered Image: the base plate plus each element as its own named, tight-cropped layer at its true position and stacking order. Connect directly, or extend with Add Layer.	LAYERS

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 059d0a1a5f5793aadda72f50b549b8b10e2ecae3ce003f82c0c28191c3460954