Loading video...

Video Failed to Load

Go Home

Our controlNET scribble preprocessor takes a flat sketch and sends it to our skybox diffusion to return an image based on a prompt that follows shapes and concepts. Still in testing, but in short, a user draws sketch, sends request, gets skybox that fits sketch. #texttoskybox

96,893 views • 3 years ago •via X (Twitter)

9 Comments

Blockade Labs's profile picture
Blockade Labs3 years ago

A before and after example of scribble preprocessor input to skybox diffusion output. Available soon at #texttoskybox #texttogame #vr #stablediffusion

MΞntis 🇦🇺's profile picture
MΞntis 🇦🇺3 years ago

Seriously - you guys blow my mind on the daily... #WenBetaTest ? 🤯

Jenny's profile picture
Jenny3 years ago

😮

Dan Rockwell's profile picture
Dan Rockwell3 years ago

LOL brilliant, frickin brillant.

Bagsy's profile picture
Bagsy3 years ago

🤯

leric's profile picture
leric3 years ago

incredibly exciting work

Noodles's profile picture
Noodles3 years ago

Oh wow how to try this tool?🤔😀👍

Blockade Labs's profile picture
Blockade Labs3 years ago

This feature is currently in development, but for now you can play with

Mr. Walkway's profile picture
Mr. Walkway3 years ago

So cool! if you then pipe it into a depth model like MiDaS could you make it a pseudo-3d environment?

Related Videos