lllyasviel
lllyasviel
I am working on my paper and I implemented a new nn to get sketch from paints. Unlike the "lnet" in paintsChainer, It can drop useless details and add lines...
 **cGAN-based Manga Colorization Using a Single Training Image** https://arxiv.org/abs/1706.06918 @powion  The author uses a "trapped-ball segmentation" to divide the painting into several parts, as a hint...
https://github.com/lllyasviel/style2paints/blob/master/paper.pdf Ok. All of my detaied methods are shared here :) The paper is submitted to ACPR 2017 and is limited to 6 pages. Additional results: https://github.com/lllyasviel/style2paints
### Discussed in https://github.com/lllyasviel/ControlNet/discussions/30 Originally posted by **lllyasviel** February 12, 2023 We plan to train some models with "double controls", use two concat control maps and we are considering using...
It seems that I already used many tricks but training still OOM for 8GB gpu. But inference is good now. This is strange because I know some textural inversion or...
### Discussed in https://github.com/lllyasviel/ControlNet/discussions/12 Originally posted by **lllyasviel** February 11, 2023 This is guideline to transfer the ControlNet to any other community model in a relatively “correct” way. This post...
Hi great plugin. I played with it a bit and the memory optimization is really good. Some considerations should be put with higher priority: 1. The requirements for some mode...
Hey mikubill, I'm trying to understand why a1111 requires so little gpu. The model itself is 5.7G and a simple read is already OOM. How is 4GB optimized?
Because the previous thread is out-of-date and many new previews are released, new thread starts here.
- [x] I have searched to see if a similar issue already exists. **Is your feature request related to a problem? Please describe.** Right now if we want to make...