u2net | u2net

I am successfully using U2Net to remove the background of images using the terminal and I am also using the nice interface of this repo to do the same thing just in an easier way and validate the similarity of the results. However, my issue is that the background removal is too strong for images like this:

Where I get the following result (i.e. packaging is also removed):

If I upload the image in Foco clipping website and I select Type=='Graphic' I get exactly the same results. That means that the website is using the same algorithm to remove the background for Graphic-type images. Nevertheless, if I select Type=='Product', then the result is the following and is exactly what I want:

Does anyone have any idea on what to do to obtain the same result?

I converted the original u2net model weight file u2net.pth to tensorflow lite by following these instructructions, and it is converted successfully.

However I'm having trouble using it in android in tensrflow lite, I was not being able to add the image segmenter metadata to this model with tflite-support script, so I changed the model and returned only 1 output d0 (which is a combination of all i.e d1,d2,...,d7). Then metadata was added successfully and I was able to use the model, but its not giving any output and returning the same image .

So any help would be much appreciated, in letting me know where I messed up, and how can I use this use this u2net model properly in tensorflow lite with android, thanks in advance ..