We're stepping into a new reality (!) Introducing EMO: a groundbreaking AI that creates expressive portrait videos from just an image and audio! 🧵 More in the thread:

EMO generates expressive portrait videos from just an image & audio! It captures subtle facial expressions & head movements, creating lifelike talking & singing videos.

Unlike traditional methods, EMO uses a direct audio-to-video approach, ditching 3D models & landmarks. This means smoother transitions & more natural expressions.

EMO even excels at generating singing videos in various styles! Imagine creating music videos with just a single image of your favorite artist!

EMO outperforms existing methods in both realism & expressiveness, setting a new standard for talking-head video generation.

Research paper from Alibaba group:

That's all! If you like what you see, 1. Follow me @doganuraldesign 2. Like and repost the first post below 👇 I'm exploring and sharing Gen AI daily. See you in another one!

Wow. This is big for the future of completely customized AI assistants. Upload a photo, choose a voice, design a personality or leave it random..

Absolutely, it'll be a significant upgrade for AI assistants

Copyright theft. We're going to pas laws that make sure companies like yours log, itemise, request and pay for every piece of copyright footage that you use.

@pika_labs in the meantime: it's good we have released lipsynching 1 day earlier 😅

@pika_labs At least they have a working web app :) As tech advances, they will improve as well ✌️