You can hover over the images to see the prompt that was used. Some keywords are added to the prompt on the backend depending on the "Art Style" used, and you can see those, as well as the seed, when you hover.

At one time in the past, the generator was saving prompt/generation information in the EXIF data of the images. The last image I have saved that contained EXIF data showed the generator was using SD1.5+Deliberate v2, 20 steps, Euler a, CFG/Guidance 7. It really does seem like there's other things going on under the hood though, because if I use those settings and input the saved prompt exactly, even including the same seed, from one of the images I have saved from before the EXIF data was dropped, I can't replicate the image using HappyAccidents. The quality is the same basically the same, but experience tells me that if I feed the exact same prompt, seed, and configuration into both, I should get the same output, which I do not, which tells me there's still something hidden somewhere.

I really wish that saved EXIF data would be brought back. It makes it a lot easier to go back to an image I saved from earlier and tweak or retouch it.

Since we're sorta on the topic - I'm not sure where it got broken, if it was something on perchance itself or something with the gpu farm you're using, but is it possible to get the prompt and generation information (seed, model, etc) back when saving images? It used to be saved in the EXIF data as a User Comment but that went away mid-August. It was really nice to be able to pull up an image that I wanted to tinker with later and reuse the prompt again.

Fear not! While I am not the creator of the original pretty-ai page, I had fortunately made my own copy to play around with some stuff after the Flux changeover. After the demise of pretty-ai yesterday, I cleaned it up and made it public: https://perchance.org/pretty-ai-flux You can use the prompt-hunter link mentioned in another comment to find old galleries, apparently.

Looking at the code, where the "generated video" should be returned, they have a hard coded constant for a placeholder overwriting the variable. It also looks like they never got the placeholder to play correctly - audio works (it's the same audio as if I view the placeholder video directly) but couldn't get the video's image to show correctly here.

There is no indication of what they were planning to use to generate the video, but the video description it pops out is pretty insane and I think it is unlikely they'd be able to find any external sources that would allow free generation of the videos it is claiming, especially at an nsfw level.