Tuxa

We are not an image hoster after all. Too many problems would be coming along also.

I cheated a little bit by creating an AI that allowed me to do it faster in a semi-automatic fashion. However, the first batch to train this "labeling"-network was generated manually, which took forever.

Yup. Multiple u-nets, actually.

I tried this during development. It works amazingly well but there are also a lot of downsides: the long processing time is just a minor example.

yup

agreed. did not expect this interest. should work again.

we are about to add new servers to handle the load

What images did you use? Could you give me an example so I can look into this?

Time, primarily

It was primarily trained on portrait shots. So not many samples with groups of people. May change in the future.