Originally made by deeppomf.

This master is not the newest version of DeepCreamPy because apperantly the decensor.py does not work out of the box with 2.2 and there is no GUI in Colab. This shouldn't matter, since the used model is uptodate.

• If you can't open Colab-DeepCreamPy-2.2.ipynb inside your Google Drive, try this colab link and save it to your Google Drive. The "open in Colab"-button can be missing in Google Drive, if that person never used Colab.
• Google Colab does assign a random GPU. It depends on luck.
• The Google Colab VM does have a maximum session length of 12 hours. Additionally there is a 30 minute timeout if you leave colab. The VM will be deleted after these timeouts.

This repository represents a deep learning-based tool to automatically replace censored artwork in hentai with plausible reconstructions inside a Google Colab virtual machine.

Before DeepCreamPy can be used, the user must color censored regions in their hentai green with an image editing program like GIMP or Photoshop. DeepCreamPy takes the green colored images as input, and a neural network automatically fills in the censored regions.

• Decensoring images of any size
• Decensoring of ANY shaped censor (e.g. black lines, pink hearts, etc.)
• Decensoring of mosaic decensors
• Limited support for decensoring black and white/monochrome images
• Generate multiple variations of decensors from the same image

The decensorship is for color hentai images that have minor to moderate censorship of the penis or vagina. If a vagina or penis is completely censored out, decensoring will be ineffective.

It does NOT work with:

• Hentai with screentones (e.g. printed hentai)
• Real life porn
• Censorship of nipples
• Censorship of anus
• Animated gifs/videos

Special thanks to deeppomf, ccppoo, IAmTheRedSpy, 0xb8, deniszh, Smethan, harjitmoe, itsVale, StartleStars and SoftArmpit. I, styler00dollar, only added Google Colab support.

Source code and official releases/binaries are distributed under the GNU Affero General Public License v3.0.

Example mermaid image by Shurajo & AVALANCHE Game Studio under CC BY 3.0 License. The example image is modified from the original, which can be found here.

Neural network code is modified from Forty-lock's project PEPSI, which is the official implementation of the paper PEPSI : Fast Image Inpainting With Parallel Decoding Network. PEPSI is licensed under the MIT license.

Training data is modified from gwern's project Danbooru2017: A Large-Scale Crowdsourced and Tagged Anime Illustration Dataset and other sources.

See ACKNOWLEDGEMENTS.md for full license text of these projects.