Frequently Asked Questions

Q. How does it work?

A. Please watch this tutorial video first.

Q. What is "Cloud usage rights"?

A. Creating Deepfake videos requires long hours of computer use on the cloud, which is expensive.
Cloud usage rights is the right to be able to use that computer.
For example, if you have five hours of cloud usage rights, that means you can only use the computer for five hours.
It takes about four to five hours of computer time to create a single video.
Cloud usage rights can be purchased for $2 for an hour.
* In advanced mode which automatically uses high spec server, 5x more cloud usage will be consumed.

Q. How many hours of cloud usage rights should I purchase to create a deepfake?

A. 5 hours usage rights($10) for the basic mode (with 10,000 learning iterations), 3 hours usage rights($6) for the advanced mode (with 1,000 learning iterations) are required to start making Deepfakes.
If you just want to face-swap(which requires the trained model), 1 hour ($2) for the basic mode, 2 hours($4) for the advanced mode are required.
Please refer to the matrix below.

Basic Advanced
Estimated creation time Required cloud usage rights Estimated creation time Required cloud usage rights
Face-swap only (no training) 1 hour 1 hour cloud usage rights 0.5 hours 3 hours cloud usage rights
1000 learning iterations - - 0.5 hours 3 hours cloud usage rights
10000 learning iterations 5 hours 5 hours cloud usage rights 1.5 hours 7 hours cloud usage rights
50000 learning iterations - - 5 hours 25 hours cloud usage rights

Q. Do cloud usage rights expire?

A. Cloud usage rights expire after 6 months from the date of purchase.

Q. When and how are the cloud usage rights consumed?

A. The estimated consumption of cloud usage rights based on the estimated creation time will be held when the creation starts,
then the actual amount of cloud usage rights will be subtracted from your balance after the creation completed. Because it is difficult to accurately predict the actual amount of time required, we calculate rough standard estimates.

Q. What are the basic plan and the premium plan?

A. Basic plan is a free plan (You need to purchase cloud usage rights separately).
The premium plan allows you to access the advanced creation mode which is a faster and flexible way to create Deepfakes for $5 monthly fee.
See the plan page for the detail.

Q. What are the basic mode and the advanced mode?

A. The basic mode and the advanced mode are the ways to create Deepfakes.
The basic mode has basic features for cration while the advanced mode allows you to change some settings such as the iteration of training.

Q. Is there a limit to the size and duration of videos that can be uploaded?

A. The maximum video size for the basic mode are 50MB and 150 seconds. 100MB and 300 seconds for the advanced mode. The format is compatible with MP4 and MOV.
It is convenient to use a website like VideoSmaller to compress the video size.

Q. Can you handle 4K, HD video?

A. Yes, for the advanced mode. For the basic mode, the resulting videos will be automatically resized to 1440px width.

Q. If the purchased cloud usage rights are insufficient, will the creation canceled midway through?

A. Once the creation begins, it will not be only partially created or cenceled due to the lack of your balance of the could usage rights. If the creation fails due to system issues, the usage rights will be refunded. If the actual amount of the consumed cloud usage rights exceeds your balance, your balance goes negative and will be balanced at the time of your next purchase.

Q. Is it possible to create a Deepfakes video even if there are multiple people in the video?

A. Since the system attempts to recognize the every faces that appears in the video, it affects in a negative way to the learning or swapping.
In the video, only the target person should appears with high precision and without blurring as much as possible.

Q. How can I improve the quality of Deepfakes videos?

1. Regarding the video you want to swap the face)
In the video, only the target person should appears with high precision, without blurring, moving and the subject is facing the front.
2. Regarding the video (or images) for training the model)
Use a video (or image) in which only the target person appears with high precision and without blurring. Also, it is better to have variations in the expressions and facial angles of person in the video. The video should be longer than 20 sec, and the number of images should be higher than 300. You can also combine videos and images.

The quality will improve by repeating learning with the same (or different) material several times.

Q. What is Loss?

A. Loss is a numerical value representing the difference between the face given as training data and the face generated by AI. The smaller the value, the better quality of the reproduction.

Q. How can I retrain the model?

A. Proceed to the creation page from the button with 'Create a new video with this model' located on the bottom of the video detail page.
To retrain the model, please upload the same video/images as the first training (+ additional materials if you have) on all 3 steps. Do not upload deepfaked one.

Q. When a creation fails?

A. There are two main causes why Deepfakes creation fails.

1. The system couldn't detect enough faces for training
Deepfakes creation needs to recognize faces from videos and images. But if AI could not detect enough faces from the learning data, the creation will be cenceled.
Since blurred or ambiguous faces are excluded in the process of learning, please upload the learning data with better reflection and try again.

2. Time out
If it takes an unexpectedly long time to create a video, the creation will be canceled.
Please change the video you are trying to swap to a shorter one, or reduce the size of the video and try again.