10 Stable Diffusion Models Tested With Optimal Settings!

[@allyourtechai]

🎨 Generative AI Art Playground: www.pixeldojo.ai/?

[@amorgan5844]

Dude, you save all of us so much time and give us tons of new knowledge. Thanks!

[@allyourtechai]

That made my day, thank you!

[@DisgustingJustinAD]

That's neat to see Pixel dojo seems to be compatible with different languages 😮😮😮

[@allyourtechai]

It is!

[@bussty3247]

Wow that's so cool, thank you! What's your favourite? Cheers for doing this.

[@allyourtechai]

Thank you! Before doing this I probably would have said Juggernaut was my favorite. Now it sort of depends on what I’m creating. Kandinsky has some really interesting looks, as does playground. Hard to pick just one haha

[@theSarinBlack]

Duuude I need an update on your 3d veg tower. I'm building one right now and saw you didn't update much about it last year. Did you retire it? Hope you're well

[@allyourtechai]

Hey! Crazy story but I actually moved to Portugal from the US, so I gave the towers to my mom. It’s winter there now, but over the summer she grew tomatoes and a bunch of other veggies. Still going strong !

[@theSarinBlack]

@@allyourtechai Oh that is awesome, thanks for that info and I hope you're having a blast in Portugal! I really appreciate your 3d channel, and used that to find you here. Best of everything to you man.

[@seanknowles7987]

I played with the consistent character model and it worked pretty well. Better than most. But I was wondering how to create full body images with consistent character on your platform? My reference image is only a head/shoulders shot and it replicates that, but it wont generate full body images. Is there a way to make that happen?

[@sergeysaulit]

Can't create an account... Says you've reached your limit

[@allyourtechai]

Thank you, fixed it!

[@masterhand9415]

first of all great video as always, now plz there is something i cant understand, im using fooocus, and i did the same prompt same everything, but the image is not good as it comes from his site ? can you tell me why plz?

[@allyourtechai]

Fooocus applies some additional changes to the prompts especially if you have any of their style buttons enabled. That would be my guess

[@masterhand9415]

thx so much that was helpul 👍

[@jjjbeastfd]

@@masterhand9415hey do you have discord i have some questions

[@natieklopper]

I kind of wish these steps could actually be like your previous video and not have an impact when kept the same, somehow the models should have some kind of normalisation state where the steps are scaled from the same constant so to speak.

[@allyourtechai]

The worst part is the guidance scale. The fact that some of the models need the scale down at 1 or 2 in order to produce a decent image means you have almost no room to adjust settings to follow the prompt better. I agree that some sort of normalization step would be awesome to sort of get everything balanced.

[@natieklopper]

Yea, not to mention that some good models or checkpoints don’t really have the best documentation either. But hey, at least it’s open sourced 😁

[@sander8142]

When will you make another AI news video? Always looking forward to those ( :

[@allyourtechai]

I’m almost back in action. Crazy few weeks I ended up in the hospital with pneumonia. Really kicked my butt which is crazy because I’m a pretty healthy/fit guy. New vids coming soon!!!

[@STREAM_BOXER]

wont let me create an account. Says you reached your limit

[@allyourtechai]

Thank you, fixed it!

[@alcocat]

ad for $$ service = dislike