BriaGuidedRemoveBackground - ComfyUI Built-in Node Documentation

This node removes the background from an image with Bria, keeping what the prompt describes. The original pixels come back at full resolution with a new alpha channel instead of being re-rendered, so fine detail and edges survive. A prompt that matches nothing returns a fully transparent image. For a plain cutout with no guidance, Bria Remove Image Background costs less.

Inputs

The moderation selector reveals additional moderation options when set to "true".

Common Inputs

Parameter	Description	Data Type	Required	Range
`image`	The image to cut out.	IMAGE	Yes	-
`prompt`	What to keep, and optionally what to drop or narrow to, such as ‘the person with the mat and the plant’, ‘the woman at her desk without the lamp’ or ‘only the chair’. Must not be empty. If nothing matches the prompt the result is fully transparent. Default: `""` (empty string).	STRING	Yes	1 character or more
`moderation`	Moderation settings. When set to `"true"`, the visual moderation flags below become available.	DYNAMIC_COMBO	Yes	`"false"` `"true"`

Moderation “true” Inputs

These parameters appear only when moderation is set to "true". The "false" option adds no additional inputs.

Parameter	Description	Data Type	Required	Range
`visual_input_moderation`	Enables content moderation on the input image. Default: `False`.	BOOLEAN	No	True / False
`visual_output_moderation`	Enables content moderation on the generated image. Default: `False`.	BOOLEAN	No	True / False

Outputs

Output Name	Description	Data Type
`image`	The cut-out image: the original pixels with a new alpha channel.	IMAGE

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): 210fa214a0d0d8ad19a15ea4f6baa9f13499bc4c3767e270f19f2a08d67e25ac

​Inputs

​Common Inputs

​Moderation “true” Inputs

​Outputs

Inputs

Common Inputs

Moderation “true” Inputs

Outputs