Martin Nebelong (@martinnebelong) 's Twitter Profile
Martin Nebelong

@martinnebelong

🎨 Exploring the latent space between creativity and Ai. Principal creative technologist at Google (through Yunojuno). Prev: Lumalabs, Media Molecule, LEGO etc.

ID: 66961750

linkhttp://Www.youtube.com/c/Martinnebelong calendar_today19-08-2009 09:59:19

19,19K Tweet

32,32K Takipçi

1,1K Takip Edilen

Martin Nebelong (@martinnebelong) 's Twitter Profile Photo

Dreams (PS4 and 5) is still by far the best Vibe-world-building tool I've used. This was 40 minutes of work from scratch 😍 All sculpted using my two hands and two move controllers. I dream (sorry) of this type of free-form creation combined with Generative AI. The best of

Martin Nebelong (@martinnebelong) 's Twitter Profile Photo

Curious to see what awesome new techniques you all discover with Veo. Between jump/cuts and annotating start-frames there's got to be a lot of new things to discover ❤️

Justine Moore (@venturetwins) 's Twitter Profile Photo

This may be the coolest emergent capability I've seen in a video model. Veo 3 can take a series of text instructions added to an image frame, understand them, and execute in sequence. Prompt was "immediately delete instructions in white on the first frame and execute in order"

Bilawal Sidhu (@bilawalsidhu) 's Twitter Profile Photo

Google just discovered a powerful emergent capability in Veo 3 - visually annotate your instructions on the start frame, and Veo just does it for you! Instead of iterating endlessly on the perfect prompt, defining complex spatial relationships in words, you can just draw it out

Martin Nebelong (@martinnebelong) 's Twitter Profile Photo

"Generative Ai will never be useful for professional work", "The topology sucks", "Look at the hands".. You should get used to the idea that things will change in a big way. Embrace it, be creative with the new tools and continue to create beautiful, exciting and surprising art

Jerrod Lew (@jerrod_lew) 's Twitter Profile Photo

Google Veo 3 understands spatial prompts. Upload an image with some annotations and ask Veo 3 to follow the instructions in your prompt. Here's how to do it, and some examples.

Always Generating (@notiansans) 's Twitter Profile Photo

You can add different camera movements to the same scene, reframe the scene in a new way, animate the subject differently than the original video etc. Aleph is (wild) and a completely new way to create 👀

Jer at EccentrismArt (@eccentrismart) 's Twitter Profile Photo

3) Then I used Martin Nebelong and Framer 🇱🇹 technique of prompting an instant cut to another shot. I mostly used Veo3 but you can also do this in Seedance or use Runway Aleph