nicollegah

woke up early, wanted to build something to visualize music in a simple way. you can choose between "concentric" and "linear" mode. what else should i add?

any information on the inference speed of this vs midas?

We recently introduced visual echos in AI animations. It is a novel way to create stable AI videos with Stable Diffusion based on ControlNet.

ahh thanks

Wait are these inference times real? 1 second on a Raspi? Do I get this right? This is faster than on my GPU. What's going on here?

looks very interesting. will try it out!

Honestly, I feel the opposite. What he imagined back then as absolutely crazy was standard only 20 years after. It is crazy how exponentials work. Wild to think where we are standing 60 years later and wild to think where we will stand in 60 years.

reading the first three paragraphs after a week like this makes me crazy.

ah sick, i didn't know that. thanks!

It should absolutely work now. Doesn't it?

looks cool. somehow the website looks screwed up in my browser (chrome) and I cannot get an API key after signing up.

Those are very good suggestions. I built it with mobile in mind but somehow I failed to get it right, yet. Will continue to work on it. Would also be nice to make a native app at some point.

Do you have some resource to learn how this works? I'd love to implement it.

I understand and have been thinking about it. Would somehow like to monetize this but if it doesn't work out I might just open-source it.

Hi all, thanks for all that attention to the site. I am super happy about that. A word of caution: I can only rent 4 GPU instances currently on AWS due to service quota limits. "Unfortunately" the traffic due to hackernews is too high for that. Sorry for any inconveniences. If you are having troubles at the moment, come back later or so. I asked for service quote increase but those take usually 24h or so.

Also, very little people actually pay so I can only afford so much.

hahaha, i think you're right.

it's on the landing page directly. You can also check https://twitter.com/neuralframes

I've set it up myself. The APIs I saw didn't seem suitable for this real-time inference thing.