zlacker

One idea I had was to try to recreate the original using a prompt. If you succeed, it should be obvious that the original was in the training set?

>>baxtr+(OP)
The LAION-5B dataset is public, so you can check directly whether a picture is in there or not. StabilityAI only takes a very limited amount of information from each individual picture, so for Stable Diffusion to closely reproduce a picture it would need to appear quite frequently in the dataset. There are examples of this, such as old famous paintings, "bloodborne box art" and probably many others, though I haven't looked deeply into it.

>>baxtr+(OP)
No, the "original" is in the (likely detailed) prompt you give it.

>>baxtr+(OP)
This is quite easy to do, but the results can be off in funny ways. For example, try putting this into SD with Euler a sampling and a cfg scale of 10:

"The Night Watch, a painting made by Rembrandt in 1642"

It generates a convincing low-res imitation about half the time, but it also has a tendency to make the triband flag into an American flag, or put an old ship in the background, or replace the dark city arch with a sunset...

If you keep refining the prompt, you can get closer, but at that point you're just describing what the painting should look like, rather than asking the model to recall an original work.