lllyasviel

http://hi.cs.waseda.ac.jp/~esimo/en/themes/illustration/

Do you think "paintschainer" itself is actually, to some extent, already a good segment network? You know, when a sketch is feeded to the paintschainer, the paintschainer always has a...

https://arxiv.org/abs/1706.06759 **Comicolorization : Semi-automatic Manga Colorization**   Hmm, so many paper related to style/color ref colorization recently. As well as "cGAN-based Manga Colorization Using a Single Training Image", all...

By the way, how you set learning rate to your very giant 600,000 dataset? In your code, the lr for adam is 1e-5, but I think it is so high....

yes i use yuv channel for lnet. I am writing the training way now.

I think the main difference between our training is the the attitude torwards details. Take "eye" as an example, your lnet has the ability to convert the eye into sketch...

You can use some standard deep learning tools as your beginning: pix2pix: https://github.com/phillipi/pix2pix cycleGAN: https://github.com/junyanz/CycleGAN Chainer version: pix2pix: https://github.com/pfnet-research/chainer-pix2pix cycleGAN: https://github.com/Aixile/chainer-cyclegan

also, to predict unconditional eps, perhaps we may also try to ignore the unet adding rather than using zero as control map, to save computation. but we may experiment a...

cool! perhaps ignoring control map on uncond is better considering some controls do not support zeros as uncond, like seg or normal map. ignoring on uncond should be better for...

I am not familiar about API is this because users enable multi controlnets but only give one unit in API? can anyone test it and see do we update codes...