Loading video...
Video Failed to Load
early results from our latest lipsync model, lipsync-2 its zero-shot so you don’t need to train every character. It edits anyone without having to see them before — while preserving their unique style really excited for this one, extremely proud of the team
12,704 views • 1 year ago •via X (Twitter)
11 Comments

@synclabs_so When will you be able to do cows and pigs and goats? @thecomedybarn wants to work with you!

@synclabs_so @thecomedybarn focused on humans for rn, but it’s interesting the problem is there is no data to learn how pigs talk from 😅

NEW OFFICIAL COLLABORATION ALERT! Get your PERSONALIZED @Godzilla_Toho Japanese hanko stamps at for yourself, friends and family! #fanco #godzilla #GodzillaMinusOne 👉

@synclabs_so Woah! 💥

@synclabs_so it’s seriously good

@synclabs_so Is he spewing Russian propaganda in your demo as well?

@synclabs_so This is amazing. Have been looking for a good lip syncing api can I use this?

@synclabs_so yes. we’ll roll out 2 soon, but 1.9 is also still solid making improvements to it everyday

@synclabs_so could you do a side by side comparison with the original video and post it?

@synclabs_so insane -- killing it

@synclabs_so teams on fire dude
