Loading video...

Video Failed to Load

Go Home

Semi-realtime Stable Diffusion image-to-image (Van Gogh style), Unity plugin based on Apple's Core ML port. The latency is about 2 seconds on M1 Max MacBook Pro.

291,867 views • 3 years ago •via X (Twitter)

10 Comments

Sean's profile picture
Sean3 years ago

Nice! Reminds me of this little experiment I did with minecraft - got it running as a mirror (2-3 second delay on 3090)

Grig ₡🌱's profile picture
Grig ₡🌱3 years ago

This is awesome! Can you pass the scene camera to it?

Keijiro Takahashi's profile picture
Keijiro Takahashi3 years ago

The repository contains it.

BLENDER SUSHI 🫶 X - 24/7 Blenderian's profile picture
BLENDER SUSHI 🫶 X - 24/7 Blenderian3 years ago

I cloned the plugin and CoreML, but not sure how to use it inside Unity Project. I could not find example project. I asked on Github, maybe there are extra steps or I miss to find anything to get this running?

Dreaming Tulpa 🥓👑's profile picture
Dreaming Tulpa 🥓👑3 years ago

Nice one, gonna put this into

IF's profile picture
IF3 years ago

Bravo, that's some unity next level dev skills, got diffusion inside unity with almost rt cam control feedback on an M1

Alchymi's profile picture
Alchymi3 years ago

Didn't parse the git, did you tryed it with ControlNet ?

Zilu's profile picture
Zilu3 years ago

@bigheeno

Mike's profile picture
Mike3 years ago

Will this run on my ipad air M1 ?

Laurence Bremner's profile picture
Laurence Bremner3 years ago

We'll soon have AI transforming our dull selfies into masterpieces 🤔

Related Videos