We've seen some remarkable advances with AI Avatars, but they have mostly been lightly animated static images. But, with the latest feature to LivePortrait, we can now drive Video To Video character sequences to our AI Films. Today we'll take a deep dive into Liveportrait. I'll show you where it shines, where it falters, and some workarounds and best practices that I've discovered along the way. This is much more than just face swapping! LINKS: Pinokio: https://pinokio.computer/ LivePortrait Code: https://github.com/KwaiVGI/LivePortrait/tree/main Hugging Face: https://huggingface.co/spaces/fffiloni/liveportrait-vid2vid Chapters 00:00 Intro 0:49 - What LivePortrait Video to Video Does 1:26 - LivePortrait Video to Video Tutorial 1:44 - Example 1 2:20 - Example 2 2:54 - Using AI Characters as Actors 3:20 - Driving Video Via the Webcam 4:20 - How to Clean Up the Output Video 4:57 - Adding in an AI Voice 5:12 - Errors and how to Solve 6:21 - Exposure and LivePortrait 7:36 - Installing 9:29 - Using Responsibly

Google Quietly Launched Its Best AI Video Tools (& Didn't Tell You)
25.3K views

Google Omni Is Nano Banana for Video
43.0K views

Seedance 2.0’s Sweet Spot Isn’t What You Think!
30.3K views

This Free AI Makes Your Characters Actually Act
27.4K views

Google’s Veo 4 Leaked... Krea Takes a Shot at Midjourney!
29.6K views

LTX 2.3 Sneaky Drop! Plus: A New AI Video Model!
29.2K views