Loading video...

Video Failed to Load

Go Home

Nearly real-time diffusion model, running locally and offline from my browser and with decent output quality. Pretty astonishing to use; but with such a tight feedback loop, the textual interface starts to feel really inadequate.

122,502 views • 2 years ago •via X (Twitter)

10 Comments

anotherjesse's profile picture
anotherjesse2 years ago

I'm super excited to see what generative artists / javascript hackers build integrating with things like this.. I built a quick prototype using @p5xjs You draw on the canvas - and it re-runs @SimianLuo's LCM after mouseup... I have a little more info here: It is so fun to be able to interactively play play with genai via drawing & code in near realtime

Diego's profile picture
Diego2 years ago

nice! in-browser inference? what stack?

Matt DesLauriers's profile picture
Matt DesLauriers2 years ago

Thanks! I should clarify, it’s running in Python and passing images to the browser with websockets. Only a matter of time before we see this tech running natively in a browser though. 😀

Kristian Muñiz's profile picture
Kristian Muñiz2 years ago

Wait, this is running in the browser or do you mean running in your machine and served to your browser?

Radamés Ajna's profile picture
Radamés Ajna2 years ago

Very cool ! Are you running LCM?

Matt DesLauriers's profile picture
Matt DesLauriers2 years ago

Yep!

Henry Daubrez 🌸💀's profile picture
Henry Daubrez 🌸💀2 years ago

A stone throw to verbal expression to replace the text-box and likely a control-net scribble to refine composition as you go. You push of this on a haptic device or tablet screen and you have a pretty instinctive way to create

Kristian Muñiz's profile picture
Kristian Muñiz2 years ago

HOW?

Jason Mayes's profile picture
Jason Mayes2 years ago

Wow. This is epic!!

Valent's profile picture
Valent2 years ago

very nice! is the rendering progressive or keystrokes firing multiple generations?

Related Videos