BeenYou Lite - L15 is up!
Give BeenYou a little freedom 😚
More curvy body with calming Details, But still a Petite
A fundamental change was made in L15!
⬇Please read the information below🙏
1️⃣Recommended Settings
- VAE is included (840000)
- Clip skip: 2
- CFG scale: 8- Sampler: DPM++ SDE Karras
Sampling Steps : 30+- Upscaler (Hires. fix): R-ESRGAN 4x+ Anime6B
Hires steps: 14
Denoising strength: 0.35
Upscale by: 1.5+- Default prompts
Pos: (best quality, masterpiece), ...
Neg: (worst quality, low quality), ...2️⃣Using Adetailer
- Main UI > Extensions > Install from URL
This fixes problems with the character's eyes and face in most situations
The default usage is to simply enable it and leave it alone✅Now you're good to go!
For more information, please continue below
ℹ️Why is my image different from yours?
I can't give you any technical help, sorry
Keep your prompts simple and correct
Tag auto complete extension to find the appropriate tags
Tags like 'Realistic, 8k, ...' sometimes ruin an image
Also These tags are often more useless than you might think
Neg Tags like 'mutated arms' are useless than you might think
Neg embedding can have a significant impact on the characteristics of a model
These are not as perfect as you might think
💝Contact & Support
⚠️Warning
You are solely responsible for any legal liability resulting from unethical use of this model
Don't use my model as bait to drive people to your paid generation service without permission
For anything other than general personal use, please be sure to contact me
Description
FAQ
Comments (19)
L11 (or L14, can't remember which) was a favorite of mine. I actually avoided it for a while because it just sounded like it was a lesser version of BeenYou from the title, but nope. It has its own distinct flavor. It's far more capable than the "full" BeenYou model, in my opinion, and the results are spectacular. I'm so happy to see this update. I'm always scared you're gonna delete a given model, so to see that you're continuing this one gets me pretty excited.
I never throw away models 😅 I'm still trying to revive the lost series.
The update cycle for BeenYou is actually quite simple, I update when I'm happy with the each face
However, starting in L15, it include some sources for the next FeelYou and NeedYou. I wanted to make it a little more artistic.
cause it's a new base, there are some minor issues with the model, so I'll continue to test with the Lite version.
masterpiece checkpoint
❤🧡💛💚💙💜🤎
WOOOW!!!
Also, will there be a sequel to Toonyou? :))
@TheArtAlgorithmist Sure. But it's not coming anytime soon
@Bradcatt Thank you)
These are so beautiful. I love the 3D look of them, and how soft they are.
L15 is very good model. Can you make inpainting model for it?
It's a bit sad it can only do one face, but at least the style looks neat
Try with some celebrities, it works very well and dont need extra files!
For example: "1 girl is Kristina Pimenova" or "1 girl is (Kristina Pimenova:1.2)" Where 1.2 is the weight working better for you (you have to find it!) Too low, there will be no resemblance, too high: it will be ugly and like a caricature.
While the style and idea is nice, sadly it seems to same-face every generation. Wish it could do more than one face!
This is because the model has a precise face.
But it knows celebrities, so for example type "1 girl is xxxx" where xxxx is the celebrity you prefer, and you can have any face you want! Play with the effect to see what number is better, for example "1 girl is (kristina pimenova:1.3)"
Low numbers will give weak resemblance, too high will give caricatural effect.
Let me know...
Not 100% sure if it's my fault, or if it's A1111 v1.5.1, but it feels a lot like img2img massively overbakes the re-rendered image.
Am I "doin it rong", or is this an issue with this model? This is the first time I have tried doing img2img on this version with this model.
Tested with A1111 v1.2.1 - getting the exact same results. Could anyone please confirm if this model should or shouldn't be used to img2img its own output?
And you are using random seed?
@dwcarr happens both with random seed and same seed.
I recommend using inpaint specialized model (such as dreamshaper)
Bradcatt are you still with us?
As you see there are many SD XL models now, much more expressive and powerfull.
Also, I noticed CivitAI is less paranoic on "petite" checkpoint, allowing them when people respect the rules, of course.
It would be a dream to restart with a new generation "RealYou R11", but for SD XL !