FAQs

Q. What is a Vub?

A "Vub" refers to a Visual Dub or video modification created using generative AI technology. It is the output you get when you combine Source Media and Driving Data.

Elements like dialogue, facial expressions, or even whole performances can be altered or substituted while preserving a high degree of realism.

Q. What is a Draft (quality) Vub?

A Draft Vub is used for creative decision-making and allows filmmakers to experiment with different storytelling options. Users can upload offline-quality media, which will be used to generate a Draft Vub.

This version can be used during the editing process until you're ready for a full-quality render. You get three trial Draft Vubs to start.

To upload a Draft Vub, you can use a variety of video and audio specs. See “Asset Specifications” for the full list of media specs. Draft Vubs take about an hour to generate.

Currently, the output file for your Draft Vub will be watermarked, mono, DNxHR SQ and in the native frame rate and aspect ratio.

Q. What is a Standard (quality) Vub?

A Standard Vub is similar to a Draft Vub but it will Generate a higher quality visual, with less artifacting, but will take longer to do so. Users can upload offline-quality media and it will take about 3-8 hours to Generate.

This version can be used during the editing process until you're ready for a full-quality render.

For uploading a Standard Vub, a range of video and audio specifications can be used. Refer to “Asset Specifications” for the complete list of media requirements.

Currently, the output file when you “Download latest render” your new vubbed file will be watermarked, DNxHR, mono and in the native frame rate and aspect ratio.

Q. What is a Theatrical (quality) Vub?

A Theatrical Vub is created once filmmakers decide that the Draft Vub meets their needs.

At this point, full/online-quality media is provided to DeepEditor, which will then train on this material and render the Vub at high quality.

Full quality media may vary for your needs. Currently DeepEditor can output up to 4k quality videos. See “High-Resolution Outputs” for more information.

Q. Why would I create a Draft Vub over a Standard Vub?

The primary consideration for selecting between the two options may be the audience for your vubbed video. While a Draft Vub produces a lower quality image with artifacts, it is quicker to generate and more cost-effective.

Q. How can I generate a Theatrical (quality) Vub?

If you're happy with your draft Vub, please contact us at support@deepeditor.app and we will be able to help you generate a final quality Vub. Please note that this is a paid-for feature.

Q. What is the format for Draft Vub and Standard Vub downloads?

When you download from DeepEditor, the file will be in DNxHR format, and mono. It will maintain the same timecode and frame rate as your original file. For further details, refer to “High-Resolution Outputs.”

Q What internet browsers can I use DeepEditor in?

At the moment, DeepEditor is only fully compatible with Google Chrome.

Q. How do I get a clean HQ quality file?

If you're happy with your draft Vub, please contact us at support@deepeditor.app and we will be able to help you generate a final quality Vub. Please note that this is a paid-for feature.

Q. I am getting image artifacts, what should I do?

DeepEditor uses generative AI which may introduce certain image artifacts like blurry teeth. If you experience those in your Draft Quality Vub, you may want to recreate the shot you're working on and supply more Training Data.

Training data is very similar to Driving Data. While training data does not direct how your Vub will sound, additional information will ultimately produce a better visual result. See “Create a New Vub” for more information.

Q. What are best practices for optimal results?

Ensure the following input conditions are met for the best results:

Head rotation: We can see both eyes of the speaking character at all times.

Head tilt: We can see the entire face. No extreme angles.

Jaw in shot: We can see the entire face. No extreme closeups.

Facial hair: Clean face to short facial hair. No full beards.

Occlusions: No objects come in front of the lower half of the face.

Lighting: All facial features are light enough to be distinguishable.

Distortion: No unusual appearances (e.g. heavy make-up or non-human).

See "Common Beginner Mistakes" for more information.

Q. Going through the entire process to create a Vub, how long will each step take?

The timing for each step is below.

Uploading Source, Driving Data and Training Data (optional) material: On average it takes less than a minute. The length and size of your files may affect this time.

Generate a Vub: Expect same-day turnaround for both Draft Vub and Standard Vub renders, depending on the complexity and length of the media. If you haven't received a notification email on completion of a Vub and things have taken longer than a day, go and check the queue to see if the Vub failed.

Download/Review your new file: Your Vub will reach your downloads folder in less than a minute for review or conform.

Render (in the Refinement tool): Rendering a change to your Vub can vary based on the amount of changes and length of the clip. It will on average take 20 minutes to render.

Q. What do I do if my Vub fails or I get an error?

Vubs can fail for a few reasons. The most common reason has to do with incorrect input specs. Please re-read “Asset Specifications” and “Media Prep” if you are having trouble.

Please contact customer support at support@deepeditor.app if you get stuck and we will be able to help.

Q. Does the audio in the Source media matter?

If you choose to upload Source media with sound it will not affect the Generated vub. Only the audio present in the Driving Data will affect your Vub.

Q. What languages does DeepEditor support?

The AI models in DeepEditor have been trained on a wide variety of languages. So far, no language has been found that the system cannot vub. The model used to create your Vub is based on an English Dataset.

Q. How do I stop a Vub from generating?

Once media is uploaded and the user hits “Generate” there is no way to stop the process at this time.

Q. What to do if the actor's face has glitches?

Sometimes a shot can get overworked, meaning that there are a lot of inputs being made over a frame. When this happens the rendered face will have a glitch.

When this happens, you can decrease interpolation on the frames that have glitching. It is a per case application. Lower it until it goes away.

This can reduce the accuracy of new mouth movements so, be mindful.

It can also show up on frames with Blendshapes that you've added. If this happens, reduce the intensity on glitching frames.

Q. Which action in DeepEditor results in a charge to my account?

When you create a Vub and click "Generate," tokens will be deducted from your account.

See how to manage & Purchase Tokens.

Q. What is the time frame for receiving tokens after making a payment?

We are diligently working to make it instantaneous, but currently, it takes about an hour. Times may vary depending on the hour and time zone.