ComfyUI 原生Recraft Remove Background节点 Recraft Remove Background 节点通过 Recraft 的 API 能够智能识别并移除图像背景，生成带有透明背景的图像和对应的Alpha蒙版。

​
参数说明

​
基本参数

参数类型默认值说明
image图像-需要移除背景的输入图像

​
输出

输出类型说明
IMAGE图像移除背景后的图像(带Alpha通道)
MASK蒙版主体对象的蒙版(白色区域为保留的主体)

​
源码参考

[节点源码 (更新于2025-05-03)] 
class RecraftRemoveBackgroundNode:
    """
    Remove background from image, and return processed image and mask.
    """

    RETURN_TYPES = (IO.IMAGE, IO.MASK)
    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
    FUNCTION = "api_call"
    API_NODE = True
    CATEGORY = "api node/image/Recraft"

    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "image": (IO.IMAGE, ),
            },
            "optional": {
            },
            "hidden": {
                "auth_token": "AUTH_TOKEN_COMFY_ORG",
            },
        }

    def api_call(
        self,
        image: torch.Tensor,
        auth_token=None,
        **kwargs,
    ):
        images = []
        total = image.shape[0]
        pbar = ProgressBar(total)
        for i in range(total):
            sub_bytes = handle_recraft_file_request(
                image=image[i],
                path="/proxy/recraft/images/removeBackground",
                auth_token=auth_token,
            )
            images.append(torch.cat([bytesio_to_image_tensor(x) for x in sub_bytes], dim=0))
            pbar.update(1)

        images_tensor = torch.cat(images, dim=0)
        # use alpha channel as masks, in B,H,W format
        masks_tensor = images_tensor[:,:,:,-1:].squeeze(-1)
        return (images_tensor, masks_tensor)