This is my finetuned base model, but in a LoRA.
This finetuned base model:
Focus on creativity, rather than a fixed style. The dataset is very diverse. So this model does not have default style (bias) that limits its creativity.
Less deformed images. More logical. Should fix the problem of overfitting in pretrained anime base models. See "Why and how this works" section below.
Only natural textures, lighting, details. I handpicked every images in the dataset. Zero AI image. No smooth plastic AI style (No same AI faces. No plastic hair, smooth surfaces, etc...).
Better prompt comprehension. Trained with natural language captions.
---------------
Why there is no default style?
What is "default style": If a model has a default style (bias), it means no matter what you prompted, the model must generate the same things (faces, backgrounds, feelings) that make up the default style.
Pros: It is easy to use, you won't have to prompt style anymore.
Cons: But you can not overwrite it either. If you prompt something that does not fit the default style, the model will just ignore it. If you stack more styles, the default style will always overlap/pollute/limit other styles.
"no default style" means you must add style (by tags or LoRAs). But when you stack more style tags/LoRAs, no style overlapping/pollution from this model. You can get the style you stacked exactly as it should be.
--------------------
Why is this "finetuned base model" a LoRA?
I'm not a gigachad and don't have millions of training images. Finetuning the whole base model is not necessary, a LoRA is enough.
I can save tons of VRAM so I can use bigger batch size.
I only have to upload, and you only need to download, a tiny 40MiB file, instead of a 7GiB big fat checkpoint, which can save 99.4% data and storage.
So I can spam update it.This LoRA may seem small, it is still powerful. Because it uses a new arch called from Nvidia, which is more efficient than traditional LoRA.
----------------------
Then how can I get the "finetuned base model"?
Simple.
pretrained base model + This LoRA = the "finetuned base model"
Just load this LoRA on the pretrained base model with full strength. Then the pretrained base model will become the finetuned base model.
Two ways to use this model:
1). Use it as a finetuned base model (Recommended):
If you want the finest and natural details and build the style combination you want, with full control.
Just load this LoRA first on the pretrained base model with full strength. Then the pretrained base model will become to the finetuned base model.
2). Use it as a LoRA on other base model.
Because why not, it's a LoRA after all.
But beware, this is not a style LoRA.
You are about to merge two base models. Simply add this LoRA to your base model usually won't give you what you expected. You may need to balance other weights (LoRAs, U-net blocks, etc.).
...
--------------
See full description here: https://civitai.com/models/971952 .
The model pages here are a little bit messy because they were duped or faked by other accounts, and were reclaimed to my account by site mod. At a least all versions are runnable now.
If you see the duplicated warning, just click the "View duplicate model", this will lead you to the page that has a clickable "run" button.
If you want to bookmark the model, bookmark this page. Other duplicated pages will be removed in the future.