I try to pin images that stand out / i personally like every 1-3 weeks
So if i unpin yours doesnt mean that i dont like it anymore just trying to keep a fresh rotation of images without completly filling the start page with pins <3
Join the Discord for questions / sharing pictures :) : https://discord.gg/gcJqAKQ5Af
If you enjoy my models and want to support me, you can now support me on kofi
(Since my patreon got disabled like a year ago & buy me a coffee banned me 4.2026 )
🛠️ Recommended Settings:
Resolution:
best results with832x1216//960x1440//1024x1024//1024x1536CFG Scale:
5–8Sampling Method:
Euler aorDPM++ 2M KarrasSteps:
20–50
Description
Small finetuning, clothes should feel more alive again + lighting changes
FAQ
Comments (25)
Comparing 2.0 to 3.0 using the same prompt, 3.0 has a little more flash, contrast, and seems a bit more detailed. 2.0 looks a little more realistic, and a touch softer. I like them both...
Ty for the feedback! After some more testing i can confirm v3's faces i a littl more towards anime style faces
Great model!, having a lot of fun with it, thank you!
i tested both sometimes having troubles but i wouldnt say its more or less then any other version / checkpoint
@Desync After some more time using it, you are right, I'm getting great pics :D
I'm editing the review
@Solvary glad to hear it! :D
I knew why you’re good at this. This Illustrious Checkpoint really deserves more love.
I've been using v2 for a bit over a week so far and it's VERY VERY GOOD.
Tried v3 for a while but it's considerably more "anime-like", so i'll stick with v2 for now.
Just did some more testing myself and i can comfirm this. if more people dont like it ill release the version without my lora merged in that causes the more anime style ish faces! Ty for the feedback!
I love it! ❤️🎉
Just wanna share feedback. So, after some testing, I think I still like version 2 more. V.2 is just super
After a few tests, V2 is superior, hope it doesn't fall off rotation
I will most likely keep both running until v4, v4 will be more like v2 again
@Desync yay, thanks for that! means a lot
@Desync Thank you very much :-)
absolute cinema
noob question here, why is this checkpoint MERGE, merge of what? I usually pull trained models only. thanks.
niceeee
not normally the kind of person who regularly uses semi-realistic/realistic checkpoints, but i've done some tests on this and the results are very pretty.
How do you control the facial differences between different characters?
It's always very hard. The complex workflow would be identify each character then use detailer to modify each of them.
Inpaint
It's called regional prompting, don't listen to the other ones saying it's impainting.
Thank you for your help, I really like your model.
I love 3.0 so I'm excited to try this!