zlacker

[parent] [thread] 1 comments
1. zamada+(OP)[view] [source] 2023-12-13 17:37:37
Like the other commenter said, these models aren't trained against images with an alpha channel. Given the same sized model that'd make typical results worse to benefit a niche case. You should be able to have them generate this style image on a background you can color key out though.
replies(1): >>ravetc+lk
2. ravetc+lk[view] [source] 2023-12-13 18:47:45
>>zamada+(OP)
Those examples look nice and would be trivial to automatically cut out/trace into transparent vector with inkscape
[go to top]