Anime Model Generation

[Eydahn8]

Am I doing something wrong with the settings, or is this type of content just not generable?
Because, on one hand, with objects or characters that already have a sense of depth in the photo, I get good results. But as soon as I switch to a 2D style, anime, in this case, the proportions get really distorted, and the faces end up completely ruined and unrecognizable.

Examples with images and video:

https://github.com/user-attachments/assets/b2484baa-da96-4256-af18-65d3cbbb510c

https://github.com/user-attachments/assets/7c224263-30ed-4289-8ea3-5966d88feae6

https://github.com/user-attachments/assets/756b6969-ff8e-4265-afbc-d35992b38229

https://github.com/user-attachments/assets/9f81f1f0-17b6-4db9-905b-2cc33362f794

[studiobloom]

these still look pretty great to me for what this technology is.

but yes i'd assume that 2d images lack the extra information the model definitely uses to generate. i also haven't had much more detail than i see in your renders with humans so far. that's not exactly an easy case for 3d generation

[Eydahn8]

these still look pretty great to me for what this technology is.

but yes i'd assume that 2d images lack the extra information the model definitely uses to generate. i also haven't had much more detail than i see in your renders with humans so far. that's not exactly an easy case for 3d generation

I hope it will be improved on this aspect, but as for the weapons, like this one:

https://github.com/user-attachments/assets/0967787e-185b-4e8b-9dfa-edc1354b4b53

I’m speechless, truly an amazing job