Does anybody here have any idea about the technology and the steps used to create virtual speaking avatars like Sana and Lisa? I know paid tools like DID and Synthesia exist, but is this what was used to create Lisa and Sana? I am actually more interested in open-source techniques and free tools that can do the same. In fact, I would be happy to know only the names of the algorithms used at each step, if that's... Source: 11 months ago

d-id.com is commonly used for animating portrait images based on a voice audio track. I'm not aware how it's done for non-portrait images though. Source: about 1 year ago

Ill have to do ore research or testing. Thanks for d-id.com, will check it out! Source: about 1 year ago

Absolute quickest way would be to look at d-id.com . This does everything for you. Source: about 1 year ago

Mine too! I used d-id.com for the voice animation and put the images together in canva.com . Source: about 1 year ago

Yes I could use generator like generated.photos but it gives you a single plain image, which is not enough to perform well. Source: about 1 year ago

Credit to generated.photos for the AI generated face. Source: about 1 year ago

When you reverse image search the photos they all come back as coming from the site generated.photos. Source: about 1 year ago

Https://generated.photos AI generated photos. Source: over 1 year ago

You can use "generated.photos" to create faces of black people but, recently it's now a paid service :\. Source: over 1 year ago