zlacker

[return to "MobileDiffusion: Rapid text-to-image generation on-device"]
1. spupy+3W[view] [source] 2024-02-01 09:11:52
>>jasond+(OP)
So what could be some use cases for this apart from as a toy or for faking photos/art?
◧◩
2. simult+XW[view] [source] 2024-02-01 09:21:02
>>spupy+3W
Generating memes to friends sparing search time. Describing sketches have them on the fly sharing with teams?
◧◩◪
3. nonran+rY[view] [source] 2024-02-01 09:39:24
>>simult+XW
People search and remember things visually. Even if they're not consciously aware. So on the Cybershow [0] we decided to jump-in and use AI images as a quick way to visually tag episodes with something meaningful and fun.

We did that despite some moral ambivalence/uneasiness around AI "art".

For example, give me a "young and exciting Dana Meadows in front of a board of systems theory"

I'm not awful at photoshopping things, and sometimes that's the only way to get a specific image one has in mind. But it saves time and lets us concentrate on writing and researching instead.

TBH if an artist/illustrator came along and said "Let me do the episode icons even though you can't pay me yet" I'd feel inclined to ask the AI to step aside.

[0] https://cybershow.uk/episodes.php

[go to top]