Request for Image + Mask Handling Support

[Six6pounder]

Hello,

I would like to request support for handling image + mask pairs in the project. This feature is essential for tasks that involve segmentation or similar image processing requirements.

Feature Request:
Add functionality to process image + mask pairs.

I have noticed that the primary functionality is controlled by the predict.py file. Could you please confirm if implementing this feature requires changes only in this file?

Thank you for considering this request.

[fofr]

Do you have a ComfyUI workflow for this?

[Six6pounder]

def handle_input_file(self, input_file: Path, isMaskFile: bool = False):
...
        if isMaskFile:

                shutil.copy(input_file, os.path.join(INPUT_DIR, f"mask{file_extension}"))
                
                
def predict(
        self,
        mask_file: Path = Input(
            description="Mask image, tar or zip file. Read guidance on workflows and input files here: https://github.com/fofr/cog-comfyui. Alternatively, you can replace inputs with URLs in your JSON workflow and the model will download them.",
            default=None,
        ),
        ....
       if mask_file:
            self.handle_input_file(mask_file, isMaskFile=True)