ComfyUI Node
Get background mask
Computes the foreground mask. It normalizes the input images, scales them to the model size, computes the masks and then scales the masks to the image size. No background removal/replacement is done. See the `Remove background (full)`.
Get background mask
- model
- images
- depths
- masks
- depths
- edges
◄width1024►
◄height1024►
◄upscale_methodbicubic►
◄mask_threshold0.000►
◄batch_size1►
◄out_dtypeAUTO►
CategoryRemBG_SET/Basic
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| model | SET_REMBG | The remove background model from `Load RemBG model by file` or any of the `Load XXXXXX model by name` nodes | |
| images | IMAGE | One or more images to process, will be scaled to a size that is good for the model. | |
| width | INT | 10240–16384 | The width of the pre-processing image, does not affect the final output image size |
| height | INT | 10240–16384 | The height of the pre-processing image, does not affect the final output image size |
| upscale_method | COMBO | bicubic | Interpolation method for pre-processing image and post-processing mask |
| mask_threshold | FLOAT | 0.0000–1 | Most models generates masks that contain a value from 0 to 1, but can be any value in between. Matte models can estimate transparency using it. If you need to make the mask 0 or 1, but nothing in between, you can provide a threshold here. Values above it will become 1 and the rest 0. |
| batch_size | INT | 11–256 | How many images to process at once |
| depthsopt | MASK | For models that starts with a depth map | |
| out_dtypeopt | COMBO | AUTO | Data type used for the outputs. `AUTO` means the same as the input.Using `float16` can help when processing videos. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| masks | MASK | The estimated masks, where a higher value means the model estimates it belongs to the foreground with more confidence. |
| depths | MASK | The estimated depth map. Either from the `depths` input or computed. Note this applies only to PDFNet. This is the map generated by `Depth Anything V2` |
| edges | MASK | The estimated edges. This is only generated by the DiffDIS model. |