Frédéric Simard’s Post

View profile for Frédéric Simard, graphic

Expert at connecting Minds and Entertainment through BCI Technology | Neurotech, Neuromarketing, CX, agentic AI, Adaptive Entertainment | Entrepreneur, Consultant & Advisor

I don't think I'm too late to the party. Here's my first Luma AI video (queued for 4-6 hours). I'm not very experienced with video generators, but I've been playing #RunwayML for the past few months. My first impression of prompt-to-video: (+) The video has much more movements and character action than anything I got with runway, like way more. (+) 6 seconds, instead of 4. (+) Runway has a protection against multiple types of scenes (some of which I definitely agree with, but some I find restrictive, if you want to explore the action and horror movie genre). This one is meant for an action movie and it wasn't blocked as too violent, which I appreciate. (-) a few more gen-ai defects than I was lead to expect, but still acceptable for now (if you're looking for that gen-ai style). (-) announced time-to-generate 120 seconds which is slower than runway (even for 50% longer sequence). https://lnkd.in/eeBgyStA Overall, the current developments pace in the field leads me to think that in a year, we'll have something like 3x faster generation and close to perfect cinematic videos every time. We'll see.

My first Luma AI video (gen-ai)

https://www.youtube.com/

To view or add a comment, sign in

Explore topics