Updated README

This commit is contained in:
deeppomf 2018-09-23 00:06:49 -04:00
parent 1d41c70a84
commit be82bde1e1

View File

@ -3,9 +3,9 @@
This project applies an implementation of [Globally and Locally Consistent Image Completion](http://hi.cs.waseda.ac.jp/%7Eiizuka/projects/completion/data/completion_sig2017.pdf) to the problem of hentai decensorship. Using a deep fully convolutional neural network, DeepMindBreak can replace censored artwork in hentai with plausible reconstructions. The user needs to only specify the censored regions. This project applies an implementation of [Globally and Locally Consistent Image Completion](http://hi.cs.waseda.ac.jp/%7Eiizuka/projects/completion/data/completion_sig2017.pdf) to the problem of hentai decensorship. Using a deep fully convolutional neural network, DeepMindBreak can replace censored artwork in hentai with plausible reconstructions. The user needs to only specify the censored regions.
# **DeepMindBreak V2 (temporary name) will be released this year! Many improvements with a UI, higher resolution, and better looking decensors! Stay tuned.** # **DeepMindBreak V2 (temporary name) will be released in 2018! Many improvements with a UI, higher resolution, and better looking decensors! Stay tuned!**
Consider waiting for V2 since V1 looks amateurish and terrible in comparison. **Consider waiting for V2 since V1 looks amateurish and terrible in comparison.**
![Censored, decensored](/readme_images/collage.png) ![Censored, decensored](/readme_images/collage.png)