正在加载视频...

视频加载失败

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

96,900 次观看 • 3 年前 •via X (Twitter)

9 条评论

Blockade Labs 的头像
Blockade Labs3 年前

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

MΞntis 🇦🇺 的头像
MΞntis 🇦🇺3 年前

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

Jenny 的头像
Jenny3 年前

😮

Dan Rockwell 的头像
Dan Rockwell3 年前

LOL brilliant, frickin brillant.

Bagsy 的头像
Bagsy3 年前

🤯

leric 的头像
leric3 年前

incredibly exciting work

Noodles 的头像
Noodles3 年前

Oh wow how to try this tool?🤔😀👍

Blockade Labs 的头像
Blockade Labs3 年前

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

Mr. Walkway 的头像
Mr. Walkway3 年前

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

相关视频