https://lllyasviel.github.io/pages/paints_undo/
Paints-Undo presents a family of models that take an image as input and then output the drawing sequence of that image. The model displays all kinds of human behaviors, including but not limited to sketching, inking, coloring, shading, transforming, left-right flipping, color curve tuning, changing the visibility of layers, and even changing the overall idea during the drawing process.
It takes your final image and sketches it out for you.
Git hub: https://github.com/lllyasviel/Paints-UNDO
I'll play with it at lunch.
Jump in the discussion.
No email address required.
You still haven't noticed that ALL anime characters look literally identical?
Jump in the discussion.
No email address required.
More options
Context
This has no practical use other than piss off artists and I am all for it
Jump in the discussion.
No email address required.
More options
Context
this is dumb, let the non-ai sites be non-ai
Jump in the discussion.
No email address required.
More options
Context
Pretty cool, I'll definitely play around with it when released.
More interested in getting partial state of image for sketch styles than videos though
Jump in the discussion.
No email address required.
More options
Context
I think it might be neat, but I wish he kept working on the Forge-UI
Jump in the discussion.
No email address required.
More options
Context
Snapshots:
https://lllyasviel.github.io/pages/paints_undo/:
ghostarchive.org
archive.org
archive.ph (click to archive)
https://github.com/lllyasviel/Paints-UNDO:
ghostarchive.org
archive.org
archive.ph (click to archive)
Jump in the discussion.
No email address required.
More options
Context