New Runway motion capture model

Quality is getting close enough to allow anons to do live video / podcasts / Zoom calls. 

Opportunity to create a text-to-video client that converts casts into vertical videos (which can be posted everywhere).

Introducing Act-Two, our next-generation motion capture model with major improvements in generation quality and support for head, face, body and hand tracking. Act-Two only requires a driving performance video and reference character.

Available now to all our Enterprise https://t.co/wnLU46yORg

Runway

Might go sign up for enterprise without any approval from finance

Source

https://x.com/runwayml/status/1945189222542880909

beat me to the punch

now I have my plans for the evening 🤝

Hopefully videos can get longer than 30 secs now

hmmm

guys pls share the best OCR API/approach for videos (recognise text on the video + provide transcript)