zlacker

[return to "We’ve filed a law­suit chal­leng­ing Sta­ble Dif­fu­sion"]
1. dr_dsh+12[view] [source] 2023-01-14 07:17:25
>>zacwes+(OP)
“Sta­ble Dif­fu­sion con­tains unau­tho­rized copies of mil­lions—and pos­si­bly bil­lions—of copy­righted images.”

That’s going to be hard to argue. Where are the copies?

“Hav­ing copied the five bil­lion images—with­out the con­sent of the orig­i­nal artists—Sta­ble Dif­fu­sion relies on a math­e­mat­i­cal process called dif­fu­sion to store com­pressed copies of these train­ing images, which in turn are recom­bined to derive other images. It is, in short, a 21st-cen­tury col­lage tool.“

“Diffu­sion is a way for an AI pro­gram to fig­ure out how to recon­struct a copy of the train­ing data through denois­ing. Because this is so, in copy­right terms it’s no dif­fer­ent from an MP3 or JPEG—a way of stor­ing a com­pressed copy of cer­tain dig­i­tal data.”

The examples of training diffusion (eg, reconstructing a picture out of noise) will be core to their argument in court. Certainly during training the goal is to reconstruct original images out of noise. But, do they exist in SD as copies? Idk

◧◩
2. codefl+69[view] [source] 2023-01-14 08:37:43
>>dr_dsh+12
You seem to be under the impression that SD can only generate original art. However, it will literally recreate existing paintings for you if you just prompt it with the title. Identical composition and everything.
◧◩◪
3. gdubs+yN4[view] [source] 2023-01-16 03:07:00
>>codefl+69
Models like MidJourney and StableDiffusion can generate very close renditions of some very well known paintings – and if it has enough of a conceptual understanding of even a less known painting, it can do a pretty impressive rendition of that as well.

But it's virtually impossible for these models to make an exact replica – a photocopy - of an existing painting, because that would make it break some laws of information theory probably. It's not a lossless compression engine. Paintings like, "Girl With the Pearl Earring" appear so frequently in the datasets that the models tend to overfit on them – which is actually not something you want when designing a model. It tends to create issues for you. But that's why a painting like that can be simulated somewhat accurately. But even then – it's never going to be 100%.

[go to top]