The most amateur looking model is Flux.Krea. It's censored, though, in comparison with Chroma. Chroma Flash Heun is supposed to run with 10 steps Heun sampler. Try that. I've tried it and it's slightly different from Perchance. There's a model patch and loras from Perchance, I'm pretty sure, so you're unlikely to 100% replicate it.
post
Perchance model is FLUX Chroma.
Easiest way to get photoreal output is to head off to getty and copy a photo caption: https://www.gettyimages.com/editorial-images
Example output on perchance generator

2025 Toronto International Film Festival - Black Excellence Brunch TORONTO, ONTARIO - SEPTEMBER 08: (L-R) Karen Chapman, Regina Taylor and Joan Jenkinson attend the Black Excellence Brunch during the 2025 Toronto International Film Festival at Petros82 Restaurant on September 08, 2025 in Toronto, Ontario. (Photo by Leon Bennett/Getty Images)
It’s def more than flux chroma. I tried that exact model and it’s missing details that perchance gets right all the time. It may be the UI I’m using (AUTOMATIC111/stable-diffusion-webui). I’m on macOS, but I have a 48 GB machine which supposedly can run these models and I am getting images out of it, just not the same ones that’s I get online.
I almost feel like perchance is combining multiple models or doing something more complex than just using a single one.
You ask for info , I give info. Why so distrustful?
all 7 comments