beautifulsoup

Okay so now it can't recognize even Taylor Swift and some other faces it was able to earlier. The dev is deliberately screwing the model over

They're training the model at a very basic level so hopefully they'll add celeb LORAs in future

There's no law

Literal 0 improvements in the last 2 weeks

We need a comeback of the old model which was SD1.5 not SDXL

Yeah, but this was not some bugfix or minor change, was it? They replaced the 1.5 years old core model itself; don't you think they should had made any announcements, like where they're showing NOW 'Notes on new model', it could have been 'Notes on upcoming new model'

Yeah, I know this model creates something very random at times, completely opposite of the prompts you had provided and if you're unlucky enough it'd even generate some bizarre and gut-wrenching imagery out of seemingly innocuous prompts

Try using different browser

Ok then state this model's Pro aspects and it has to be more than 4. I know one of them would include furry and cartoons anyways

The way the devs blatantly replaced the old model overnight, like it was worthless or something, shows how little they care about their own community

Any news on this?

Perchance has downgraded itself