10 Stable Diffusion Models Compared!

Today we test 10 different stable diffusion models side by side with the same prompt.

[reelmagicfilms]

I wouldn't run them all at the same CFG, steps, and scheduler because they all have different requirements. Dreamshaper in particular requires SDE Karras specifically and can't take more than about 2 CFG and 7 steps or it will start looking really burned like that. You can't really compare a Turbo and a regular model at the same settings. If you're going to test them, you should test them at the settings recommended by their authors. Otherwise it's not apples to apples. When I do this kind of testing, I do an XY plot on each model to get a handle on where it lands at different settings, and then compare my XY plots.

[freneticfilms]

Juggernaut v9, you need to lower the cfg... Then it gets less contrast and looks more natural

[HareyMon]

For photorealism, SDXL Base is still the best, imo.

[bussty]

Great test thank you. I think you should rerun this test at recommended Sampler, CFG's and Steps as found in Civitai as my experience with some of those weird results are way better when those recommendations used. A great idea and would love to see the very best each model can do with the same prompt. Love the channel!! Many thanks

[ranjithgaddhe]

I was most impressed with realistic stock photo 2.0 for realistic photos

[darkman]

ADetailer is a must to correct hand and face problems. Doesn't work right every time, but it helps greatly.

[siddharthmishra]

Awaiting for your SUPIR installation for A1111😊 12gb version

[dahozabich]

If you used the inference steps that the models documentation call for, you would get better results. We can't judge a model if we use it incorrectly. ie If a turbo model calls for 4-6, and we give 20... well... the results will be way off.

[robadams]

All these models need different settings so I think doing a comparison would mean more if they were used. Dreamshaper Turbo needs a specific scheduler, a very specific sampler, a CFG of 2 and steps of 8 to 10. You will get a horrible fried results using a high CFG and too many steps.

[darkman]

If you want red eyes, try vampire in the prompt

[amorgan]

For photo realism i still prefer epicrealism on sd1.5 with the right prompts and lora the output is insane.

[vcu]

Text 2 image Photo real Portraits are already pretty much good since SD 1.5, with the right models, there just insn't really much room for them to impress people any more TBH.. Image gen AI /LLMs really need to show off some new tricks if they are to keep the same momentum of intreast. Or else I think all this stuff could stagnate. The control nets, Loras and no censorship are what really give SD the edge.

[darkman]

cyberrealistic is pretty good, as is deliberate

[johnfl]

Not all teeth are perfect, I wouldn’t judge too much on that if the model was exposed to dynamic assortments

[loubakalouba]

Sorry to say this but using the same settings is a fail, all these models have different requirements, like boiling a chicken the same time as an egg.

[yinoveryang]

Most people that generate AI imagers (at least as a hobby) actually PREFER very fake looking imagery. They cannot tell what true realism actually is. For true photorealism, you're better going to models prior to stable diffusion XL. All images, even those with checkpoints bundled on them, look a tad fake with SD XL

Most of these models are trained and produced in Europe places like Denmark. The expression "Ruby eyes" presumably meaning bright red iris, is only an American expression. That's a "tall ask" for any AI model, as they are all trained on hundreds of thousands of images of normal people