Generator mademby folks are more like front end rsther than the actuall model. So you can use any perchance generator out there, it will more or less give same result since they usse same model.

Fyi, afaik since i starting use perchance since late 2024, there's been like 2 time major change on perchance model. The first one on late may 2025, this change from classic stable diffusion to flux (i guess, that what people say). Then on august 2025, they watered it down to what we know today. Maybe theres more changes, but that two are the mos noticeable changes.

Grok with billion dollar server can't handle imagine request and had to put down the imagine service from free public and make it paid only, no chance perchance will do the same, it already good as is. Also, there's no such limited as people would always create 20 different accounts.

now, here what i understand within my grasp about perchance, i'm not an ai expert or coder or programmer, just your yet another regular user.

those generator (all really) are simply just a "front end" to serve you to use real perchance generator, some are simple and some more advanced with fancy setting, all can have their own names. You can create one of this "front end" and name it "SD generator" or "SDXL generation" for yourself but in the end they use the same current model that being used by the server.

All of those advanced fancy setting are just adding extra prompt words to the generator without you knowing it, you can check it by generating an image with only one prompt words, after images generated, click the "i" on the top left corner of the images to see what prompt being added by using those fancy setting.

so no matter who generator you using now, they are still using same model, for this reason, you will never achieve the same image result.

again, i'm not an expert, just user, take this info with grain of salt.

Pre May 2025, i guess they use SD, this is the time where we can use (example:1.3) in prompt and use negative prompt, lot of character recognized whether it fictional or real.

Post May 2025, they say they use Flux, no more (example:1.3) or negative really being accounted to generation, but i still like it since it generate great oil painting or painting in general, still high prompt2image accuracy, prompt still recognize painter name style, like greg rutkowski or alexi zaitsev. me personally like this version much...

Post August 2025, thing gone ashtray, lot of generation artifacts or simply generating random stuff, gradually fixed and improved till now (that what they said), but imo never reach the peak pre august 2025.

Btw, i kinda like this recent one, it's improved if you generate painting style image.

Pre 8 august 2025, the image gen already use flux, me too like flux better than SD, but in my preference opinion, back then (pre 8/8/25) the quality are just way better, better accuracy, plenty artist style or library of characters are recognisable.

Now things seems to be more toward anime stuff, try "wednesday addams", "ramona flowers" or even "princess peach", how many image generated actually resembles the said characters.

i just wish it revert back to pre 8 august "nerf".

Lo, the Savior hath spoken... Thank you savior. Can't for the improved text to image gen.

Use seed perhaps? Generate some, pick one you liking, click the info icon on top left corner of the image your choice, click include seed checkbox... You can generate image with same resemblance.

I wish it returned as before, not seeing the 8 August notice anymore, I couldn't achieve the same level of generate image as pre 8/8.

I used to generate nice impasto style painting or the one with brushwork, now everything turned too smooth or anime...