SeekYou - Mikan is up!
Yet Another fluffy Anime Model
Mikan and Momo are purely a matter of taste
It has some pretty deep potential 🙂
⬇Please read the information below🙏
1️⃣Recommended Settings
- VAE is included
- 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 (23)
It's a bit more for my taste than an upgrade
They're similar but different, so you can pick your favorite and download it 😃
Can you give a bit of guidance about what to expect between the styles of Mikan and Momo?
Love this model!! very versatile and expressive
Ingredients of the merge?
jw, what does it really matter at this point?
Merges are probably containing A LOT of models, my own mix I've been working on I've gone through 100+ versions of and lost track of what was actually in it awhile ago.
Not trying to come off like a jerk or anything asking, genuinely wondering what the actual value is at this point?
@Fenn curiosity?
Base Model Counterfeit-V3.0 + my LoRA 1+ my LoRA 2 +Samyang
If you look closely at my models, except for BeenYou, you'll notice that there are some similarities. This is the influence of my LoRA 1. Additionally, 2 is a cute, slightly reduced Japanese style LoRA made just for SeekYou.
I don't use more than one model, because the base models have already been merged more times than I can count anyway.
Normally, when I base a model on someone else's, I tend to completely change the characterization, but for SeekYou, I kept the greatness of Counterfeit. It's a really good model.
Additionally, SamYang is like a little extra seasoning to anything I do.
@Fenn
>Merges are probably containing A LOT of models, my own mix I've been working on I've gone through 100+ versions of and lost track of what was actually in it awhile ago.
This right here is why I ask. "IDK what's in it lol" is a huge red flag in anyone making anything. Merging is fine, I guess, if you know what you're going for and you're careful about it, but just smashing together a bunch of stuff you like... you tell me why you think that could work.
Much better to either take an existing model close to what you want and train a lora/embedding for the difference, or if there is no model close to what you want, train your own with a big, diverse, well-tagged dataset (again, starting from an existing model). If you want the best of two models, train on both their datasets or get creative where the data's unavailable.
love your work as always <3
每一次跑兄弟你的范图就是一种享受！
Alpha 1 is better, flat, unique. Alpha 2 started looking like others.
Yeah, it's definitely not an upgrade... so I renamed it to not imply it's a higher version
All I see is Mikan and Momo. Which is which?
@Everfy Mikan is the newer one. I like both.
Man, you should do tutorial. We could learn so much from you !
I just sit back, look at the results, and drink my coffee 😊
Your checkpoint is excellent, but it's hard for me to tell the difference between this and toonyou.
This model is one of many futures for ToonYou
As I updated TY, it became more beautiful with Japanese styling, but it lost a lot of that early Alpha feel, and that wasn't the path I wanted to take. so I isolated that direction and that became SeekYou.
So there are inevitably similarities, but there are more differences than you might think, starting with the materials.
Anyway, thanks for liking my models 🙂.
two models will be moving further away from each other over time
Is there a tutorial for using ADetailer? I started recently and I haven't been able to find much, and my own experiments always look subpar.
As far as I know, once you install the extension, the corresponding .pt model is automatically activated. It has its own prompt window, but most of the time you don't need to enter it and it works fine on its own if it's just turned on. You don't need to use it at the same time as webui's own restore face feature.
extension is pretty straightforward, auto-i2i the face (especially the eyes) at the end of image generation.
Amazing work, keep it up <3
I don't understand what is wrong. When I use this model. I just get a glitchy, garbled grey image. It doesn't work.
My other models work fine. I used the prompt and setting in from the sample image.
Any help?
Done downloading the model then the model is not in my list …itry to re upload but it keep the same issue… i think the file is broken