Furry Technologists

1307 readers

1 users here now

Science, Technology, and pawbs

founded 1 year ago

MODERATORS

[email protected]

Snapchat Engineer Designs AI-Camera That Runs Stable Diffusion To Turn Your Photos Into AI Art (www.yankodesign.com)

submitted 1 year ago by [email protected] to c/[email protected]

10 comments fedilink hide all child comments

Just what nobody wanted

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 9 points 1 year ago (1 children)

A simple camera module feeds images to the DreamGenerator’s Raspberry Pi computer, which runs an instance of Stable Diffusion and ControlNet to create AI art based on said image.

The device doesn’t look large enough to house a regular Pi. Is he using a Pi Zero? If so incredibly impressive.

[–] [email protected] 13 points 1 year ago (1 children)

From the article:

AI generative tools usually require an immense amount of GPU and computing power – well beyond the capabilities of a Raspberry Pi, which leads one to believe that the AI generation happens over the cloud.

So probably the smallest piece of hardware that can establish a network connection.

[–] [email protected] 1 points 1 year ago* (last edited 1 year ago)

Tbf, Stable Diffusion can actually run on some pretty low-spec hardware these days. That said, it wouldn't surprise me if it was indeed run on cloud hardware, especially given the creator's resume.

Edit: Also, to refer to the previous comment, not happening on a Pi Zero. Just to head off that comment, lol.