Hi Perchance team!
I’ve been delving into the world of AI image generation, and have found that the Perchance generator is head and shoulders above pretty much everything else, and ridiculously fast. I’m very impressed, and was wondering if you might indulge me with a few questions?
To preface, I feel like you can’t be getting good value out of me as a user - I’m frequently generating a ton of images, and only seeing occasional ads. To that end, I’m trying to shift my heavier usage to my own local Stable Diffusion instance, but don’t seem to get the same quality of results.
Completely understand if you want to keep the secret recipe a secret - but if you’re willing to share - what checkpoints/LORAs/etc. are you using? My best guess is SD1.5 + Reliberate, which gives me better results than the other checkpoints I’ve experimented with, but it’s definitely not the whole picture.
I also wanted to ask if you guys accept donations, or have a way for me to shout you coffee, beer, courvoisier, or whatever. :D
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.