RunwayML
Create impossible video
Start new thread

Runway Act-One - Generate expressive character performances with video inputs

by•
Act-One is a new state-of-the-art tool for generating expressive character performances using video and voice performances as inputs. It represents a significant step forward in using generative models for expressive live action and animated content.

Add a comment

Replies

Best
Hunter
📌
Truly insane.
This is a game changer, a lot of animation and motion tracking studios are already biting their nails. This could potentially revolutionize the animated content generation industry in unimaginable ways.
This is so cool! I'm wondering if this can be used for really big animation projects some day (like in Disney)
Love this. This is going to be huge for expressive storytelling. Always a Runway fan :D
There will be many scenarios for use, but I have two questions: 1. Due to copyright issues, it is currently impossible to use some existing IPs, right? 2. Is it possible to customize the image?
This changes things. How accurate are the facial expressions, really? Thinking of all the indie animators who could use this... 🤔
Yooo. Think about how advertisers and others can use this to let their creativity run wild. I know this will be such a valuable tool for everybody.
It's incredible! I see great potential for sign language, where not only the hands but also facial expressions are key.
This is so interesting, I would love to try it out!
So much fun, so many ideas. So little human work involved...
12
Next