Connect with us

App Development

Official DeepNude Algorithm [v.1.]

Published

on

The original www.DeepNude.com Software and all its safety measures have been violated and exposed by hackers. Two days after the launch, the reverse engineering of the app was already on github. It is complete and runnable. So it no longer makes sense to hide the source code. The purpose of this repo is only to add technical information about the algorithm and is aimed at specialists and programmers, who have asked us to share the technical aspects of this creative tool.

DeepNude uses an interesting method to solve a typical AI problem, so it could be useful for researchers and developers working in other fields such as fashioncinema and visual effects.

I’m sure that github’s community can take the best from this controversial algorithm, and inspire other and better creative tools.

This repo contains only the core algorithm, not the user interface.

How DeepNude Algorithm realy works?

DeepNude App uses a slightly modified version of the pix2pixHD GAN architecture. If you are interested in the details of the network you can study this amazing project provided by NVIDIA.

A GAN network can be trained using both paired and unpaired dataset. Paired datasets get better results and are the only choice if you want to get photorealistic results, but there are cases in which these datasets do not exist and they are impossible to create. DeepNude is a case like this. A database in which a person appears both naked and dressed, in the same position, is extremely difficult to achieve, if not impossible.

We overcome the problem using a divide-et-impera approach. Instead of relying on a single network, we divided the problem into 3 simpler sub-problems:

  1. Generation of a mask that selects clothes.
  2. Generation of a abstract representation of anatomical attributes.
  3. Generation of the fake nude photo.

Original problem:

Dress To Nude

Divide-et-impera problem:

Dress To Mask
Mask To MaskDet
MaskDeto To Nude

This approach makes the construction of the sub-datasets accessible and feasible. Web scrapers can download thousands of images from the web, dressed and nude, and through photoshop you can apply the appropriate masks and details to build the dataset that solve a particular sub problem. Working on stylized and abstract graphic fields the construction of these datasets becomes a mere problem of hours working on photoshop to mask photos and apply geometric elements. Although it is possible to use some automations, the creation of these datasets still require great and repetitive manual effort.

Computer Vision Optimization

To optimize the result, simple computer vision transformations are performed before each GAN phase, using OpenCV. The nature and meaning of these transformations are not very important, and have been discovered after numerous trial and error attempts.

Considering these additional transformations, and including the final insertion of watermarks, the phases of the algorithm are the following:

  • dress -> correct [OPENCV]
  • correct -> mask [GAN]
  • mask -> maskref [OPENCV]
  • maskref -> maskdet [GAN]
  • maskdet -> maskfin [OPENCV]
  • maskfin -> nude [GAN]
  • nude -> watermark [OPENCV]
DeepNude Transformations

Preparing environment

Before launch the script install these packages in your Python3 environment:

  • numpy
  • Pillow
  • setuptools
  • six
  • torch
  • torchvision
  • wheel
  • opencv-python

Install Models

To run the script you need the pythorch models: the large files (700MB) that are on the net (cm.libmm.libmn.lib). Put these file in a dir named: checkpoints.

Launch the script

 python3 main.py

The script will transform input.png to output.png. The input.png should be 512pixel*512pixel.

Source – https://github.com/axuew/deepnude_official-master

How to lunch DeepNude Algorithm online?

Use any of this tools – https://nudify.tech/download-apps-like-deepnude-alternatives/ every piece is tested and evaluated by us. Almost all are Free, no registration, no downloads. We have already spent more than 200 hours testing them.

Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Number of published posts: 278 | Total number of media files: 14917
Estimated time to read all posts: 17 hours, 55 minutes. Enjoy!

© Copyright Nudify Tech 2022-2024 hello[@]nudify.tech / This blog serves exclusively for the purpose of informing interested individuals about the latest Deepnude technologies. When you use links on our website, we may earn a fee.