UPDATE: Following the common practice, the most recent version is trained on NAI with clip skip 2
The advantage of my models is clearly the ability to put multiple characters in a same image
(I was considering training a full model with the same dataset as well, but the LoHa seems to be reasonably good at this point
The other models are otherwise trained on ACertainty
Please check the version notes for further details including the clip skip to use
Normally you should be able to use the lycoris models on a lot of different checkpoints. In case of incompatibility, you can lower lycoris weight or better, merge your base model with AC/nai.
More checkpoints can be found on the associated hugging face repository https://huggingface.co/alea31415/oshinoko
Screenshots and fan arts are respectively tagged with aniscreen and fanart. Using aniscreen gives both stronger anime style and better resemblance. Using aniscreen on style models may cause weird effects.
You may want to use ; to separate characters (see the prompts of the example images)
Characters
EP01
HoshinoAi (add hair ornament if you want)
AmemiyaGoro
TendojiSarina
Aquamarine baby
Aquamarine child
Aquamarine
Ruby baby
Ruby child
Ruby (add red ribbon if you want)
ArimaKana child
ArimaKana (I suppose you should add some hat)
SaitoIchigo
Miyako
GotandaTaishi
KurokawaAkane
Main improvement of EP02
Aquamarine
Ruby
Added in EP04
NarushimaMelt
KaburagiMasaya
KichijoujiYoriko
ShiranuiFrill
KotobukiMinami
Added at the end of the season
MemCho
KumanoNobuyuki
SumiYuki
MorimotoKengo
Pieyon
Comments on the most recent model:
Pieyon is not learned very well as can be seen from the example images, showing this is a more difficult task than learning the appearance of the characters
The star-shaped eyes are learned pretty well in the newest model, probably too well that it sometimes wants to put it on other characters, especially when we do inpainting
You may want to avoid this by putting related keywords in negative
I suppose this suggests a sort of character blending
Someone reported to me the EP04 version has more important character blending compared to the EP02 version
I am not sure how it would be the case for this new one as I do not have an objective way to judge this
Hopefully it works fine for you
Dataset composition
fanart 2432
screenshots
EP 01 1268
EP 02 357
EP 03,04 777
EP 05-11 2582
regularization ~35K
--
I don't need support or credit, but I would be glad to know that you are using the models I trained and find it useful.
Moreover, I would like to advocate for more franchise models.
You can take a look at my workflow https://github.com/cyber-meow/anime_screenshot_pipeline if you are interested.
You may also check this nice page https://civarchive.com/articles/262/directory-of-girlpacks-character-packs for a collection of such models,
Description
Trained on clip skip 1.
Up to this point, Aqua, Ruby, Kana, and Akane are only trained with limited fan arts, so the quality of these characters will be largely improved later after more episodes come out.
The model is trained for 42647 steps and there are in total 4 checkpoints here
This is the 32783 step version.
If you want to put the star in the correct eye for Aqua and Ruby you would have higher chance to success with 32783 and 42647 step checkpoints. However, the last one seems to be quite overfitted. It would be much more difficult to achieve that with earlier checkpoints and extracted LoCons. For comparison please see the last four images in the examples.
On the other hand, for some characters with few training images, TendojiSarina notably, you may want to use earlier checkpoints or LoCon with lower weight to gain more flexibility.
You may want to add red ribbon for Ruby.
FAQ
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.