Book Image

Exploring Deepfakes

By : Bryan Lyon, Matt Tora
Book Image

Exploring Deepfakes

By: Bryan Lyon, Matt Tora

Overview of this book

Applying Deepfakes will allow you to tackle a wide range of scenarios creatively. Learning from experienced authors will help you to intuitively understand what is going on inside the model. You’ll learn what deepfakes are and what makes them different from other machine learning techniques, and understand the entire process from beginning to end, from finding faces to preparing them, training the model, and performing the final swap. We’ll discuss various uses for face replacement before we begin building our own pipeline. Spending some extra time thinking about how you collect your input data can make a huge difference to the quality of the final video. We look at the importance of this data and guide you with simple concepts to understand what your data needs to really be successful. No discussion of deepfakes can avoid discussing the controversial, unethical uses for which the technology initially became known. We’ll go over some potential issues, and talk about the value that deepfakes can bring to a variety of educational and artistic use cases, from video game avatars to filmmaking. By the end of the book, you’ll understand what deepfakes are, how they work at a fundamental level, and how to apply those techniques to your own needs.
Table of Contents (15 chapters)
1
Part 1: Understanding Deepfakes
6
Part 2: Getting Hands-On with the Deepfake Process
10
Part 3: Where to Now?

Summary

Data is critical for deepfakes, as with all AI. Getting the best data is a skill that you have to learn over time. It’s something that you will get better at as you become more experienced with deepfakes. That being said, some tasks can be learned without heavy investment in the process. Cleaning and organizing your data is important – time spent on this can save you time later since your AIs will be less likely to fail.

Filming your own data is sometimes necessary and can get you the best results, as this will give you enough control to fill in missing data or match limited historical data. When you have nothing but historical data, you’re more limited and may need to do further work to improve the data you have. Upscaling and filtering are possible, but you must be careful, as some techniques can add artifacts that interfere with training.

In the end, data is the most important part of training a deepfake and therefore is the most important job...