I don't understand why the change in results. used to be it was possible to create wonderful painting styles, realistic, Beaux-Arts, academic, vintage pulp, Art Deco or realistic looking old photos etc and now the results are so childishly cartoonish as to be useless. The same as on any other run-of-the-mill AI generator.

I simply do not understand why the wonderful quality that set Perchance apart is seemingly abandoned. The update that was implemented begin August 2025 was superb. Why degrade now?

Is this a temporary thing or a long-lasting change? Leave well enough alone.

I'm really sorry, but the generator is degraded. Images tends towards the cartoonish, anime or manga, really junky imaging that can done on any run-of-the-mill AI generator. Used to be before, you could make wonderful artistic images in an academic, Art Deco, vintage, beaux-Arts, representational art style, like Norman Rockwell covers or pulp fiction covers. Now it is virtually impossible to get that done. The default always pushes back towards cartoonish, childish stuff, big heads, large eyes, narrow waists on people.

This is so sad. Especially with all the months and months of work put into experimenting with and trying out prompts. Now you can get a good working prompt and two days later it produces lousy images. Can't be counted to work again. And all the work, time and effort put into making hundreds of good working prompts is all down the drain. And I surmise that when** yet another upgrade** is introduced, any prompts that work well now, will also end up being useless. Constant unasked for change ruins good things.

Yes, I too would be willing to pay IF the older model were reintroduced, the model prior to Jan 2026.

When you get totally different results with the same prompt a day or two later, it is NOT a skill issue. It is an issue with consistency and never ending changes and updates. Enough people have commented on how results always tend towards cartoonish looking images, no matter what the prompt. The generator was magnificent from Aug 2025 to jan 2026. Then the update which was a downgrade and it is like wading through molasses to get anything like the previous results. If you want cartoonish, anime, manga or simplistic results, the new version probably doesn't make much difference. But serious artistic imaging, realistic, academic, beaux arts, art deco, bauhaus, representational art is now out of the picture. A real shame.

The update of August 2025 up till a few weeks was superb. It produced artistic looking images in a variety of serious academic styles that I have never seen elsewhere. Beautiful realistic beaux arts, belle epoque realism, art deco, vintage pulp art, art nouveau, modern realism, gouache, watercolor's or even fine colored pencil and so on.

There was finally the possibility of creating images that weren't only anime, manga or cartoons like in all of the run-of-the-mill AI platforms. Finally a truly artistic rendering platform.

And now, no matter what I try, it's as if two or three steps backwards has been taken. Impossible to render anything serious anymore. I just don't understand why these present changes were implemented.

I would love to find one too and I have been searching. Nothing comes up though.

I am having the same problem. I obviously save prompts that have been giving excellent results, but yesterday (Jan 21) no matter which prompt I used, they all gave comic/cartoon results while ignoring about half of the parameters given in the prompt. No matter which art style is chosen, the results are always so cartoonish and far off with the details/settings etc given in the prompt.

Thanks for answering ... I tried putting this negative prompt in. I hope this is the correct manner to put it into a prompt? Placed at the beginning of a prompt (or at the end?)

(negativePrompt:::wrong anatomy, cartoons, cartoon style, extra legs, extra arms, anime, manga, wrong anatomy, bad proportions, duplicate faces, duplicate hairstyle, oversaturated color, amputated limbs, warped anatomy, missing limbs, deformed limbs, distorted body, incomplete body, two heads on one body, unconnected arms, unconnected legs, three legs, three arms, poorly drawn hands, poorly drawn feet, poorly drawn face, extra limbs, disfigured, deformed, bad anatomy, low contrast, distorted face, twisted limbs, twisted hands, missing arms, missing legs)

The version from Aug 2025 to Jan 2026 was amazing and allowed rendering of images in very beautiful artistic academic styles (Art Deco, Beaux Arts, Social Realism, Impressionism etc etc), without images looking cartoonish or anime. That can be done on virtually any AI platform.

As for getting spooked. The new version now working gives just as 'spooky/erotic' content as before. That hasn't changed. But the difference is simply in the artistic quality. Not every image has to be a cartoon or manga/anime. True artistic realism is hard to find on AI platforms. I don't know why this preference and pushing towards anime/cartoon stuff.

It is so utterly sad to see that gone.

I am experiencing exactly the same disappointing results. Used to be I could generate really outstandingly different results than on a run-of-the-mill AI generator that made virtually nothing but cartoons, anime and manga. The previous version of perchance allowed for great looking Art Deco, vintage pulp covers, academic and social realism images resembling real artistic results and so on ... something else than cartoon anime. Now it is almost nothing but cartoonish stuff, very unrealistic. I've also read in other comments that Perchance no longer uses Stable Diffusion, though what that exactly means is somewhat beyond me, only that it now gives different results, very very different results. A real shame because up till a few weeks ago (almost a month now I think) Perchance was truly outstanding and different.

I don't understand why there are such utterly different types of results these last days/weeks. No matter what option you use for an art style, results always seem to tend towards the same types of imagery, too much shiny, glistening AI comic book figures. The update from Aug 8 gave wonderful results in all kinds of art styles with many great looking results. Why this constant updating?

Not sure if this the one, but here is in any case a perchance based generator that allows for the altering of an already generated image ... I've found it pretty useful

https://perchance.org/...

I got those results in the previous version of Perchance ... but usually by happenstance it seemed. You could specify uncircumcised but the results were usually random ... in the present version I would not know how.

I don't think you are the problem with the cartoonish style results. I get the same cartoonish results with prompts that used to render into almost academically realistic imagery. It is heartbreaking to see the cartoonish results now.

If it is any consolation, you are describing exactly what i am experiencing: loss of realistic quality with practically all results being rendered as cartoons and with mangled and mixed up limbs far far more often than prior to this latest update ... So sad to see a wonderful version downgraded for no reason that I can understand.

Tnx for the news. This is more than I have gleaned so far. Still sort of begs the question: why not revert to the previous version?

Wow. Now this is very very good. Truly so. many tnx for making this very useful variation.

Just as an added question: is it possible to upload existing images and apply the variations function? That would really add yet more useful functionality to your version.

Also wondering if it is possible to add other art styles? For instance more realistic or academic art styles, say Art Deco, or Bauhaus, 1930s Pulp, Belle Epoque, Beaux Arts and such styles?

Once again, tnx for your work.

Tnx for the prompt. I've tried a few dozen renders and your 'prefix' does help a bit. I'll try many more times with some permutations and such and see how it works. But still, it's tricky and not really the same with some cartoonish elements showing through, like too much contrast on skin tones accentuating the muscles and such. And I used perchance for more academic artistic painting styles, not really for photos. Maybe I'll get those back with some experimenting, but I bet not entirely if the underlying Stable Diffusion is no longer used.

But in any case, tnx for the tip. I appreciate it.

I can't say it has made rendered images worse, at least not so far. I thought however that negative prompts were an important aspect of how images turn out?

Is there a reason for leaving the negative prompt out or is it a temporary thing/glitch?

I've made some 10s of thousands of non-cartoonish renders since June of 2025, in the traditional art styles that I prefer and that you think of as 'slop'. That was something no other AI platform could do that I know of. The results were wonderful. No cartoons, no anime, no manga if that was not what you were trying to do. And I wasn't nor ever will.

Cartoon render platforms are everywhere. In the galleries there isn't one image that I have found that has appeal (I stopped looking after a minute or two. They are all the same).

The question remains the same: used to be that the platform allowed rendering of images that were quality-wise miles above other platforms and in truly serious historically significant artistic styles. Why downgrade the quality? Perchance was unique in that ability.

I am not alone in this. That should be apparent from other comments.

And as others have written, if it is a question of finance (as so much is) to get that quality back to how it was, I would be willing to pay. Because it was so unique before this latest version.

There are some comments here saying the negative prompt did nothing, which is why it was removed. Well, more than a week on and from the results I get regularly, there is a much much higher incidence of getting mangled, contortioned, jumbled limbs, extra limbs, twister limbs, melted faces and all the shortcomings associated with early versions of AI. From which I cannot help but conclude that the negative prompt DID very much help with making better renders.

I also read that the negative prompt is still here. If so, where can it be accessed?