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

This is interesting. The closest I can compare it to is lobe.ai. Source: over 1 year ago

Lobe.ai says object detection is coming soon. Source: over 1 year ago

I need urgent help please!!! I've just installed the new Version of lobe.ai on my MAC and now, after it has finished, the prediction rate has decreased from more than 90% to 50% :-( :-(. Source: almost 2 years ago

Using lobe.ai 0.10.1130.5 I successfully trained using my Webcam Logitech C920. The camera turned live, and I could take individual and rapid-snap photos. But after proceeding to 'Use', the camera button does show, but nothing happens when I press it, not does hovering raise a floating menu. What am I doing wrong? Source: about 2 years ago

I'm having similar AttributeError . Wondering if this is due to the recent version changes in lobe.ai? Source: over 2 years ago