Illustriousベースのモデルを使ってマージしました
バージョンごとに大きく変わっているかもなので
お好みのバージョンをお使いください
(google translation)
There may be significant differences between versions, so please use the version you prefer.
サンプルイメージの設定は以下。reforge使用
The sample image settings are as follows:
Sampler：DPM++ SDE
Schedule type：Automation(Karras)
[Normal]
Step：6～12
CFG Scale：4～6
[DMD2 ver.]
Step：4～
CFG Scale：1
＝＝＝＝＝＝＝＝＝＝
v17.0
使用モデルを一部変更。LoRA未使用。
Some changes were made to the model used. LoRA was not used.
v16.0
使用モデルを一部変更。LoRA未使用。
Some changes were made to the model used. LoRA was not used.
v15.1
15.0を少し組み直しました。15.0も残しておきます
I rearranged version 15.0 a bit.I'll keep version 15.0 as well.
v15.0
使用モデルを一部変更。LoRA未使用。
Some changes were made to the model used. LoRA was not used.
v14.0h
v14.0にLoRAマージしたもの。14.0より少しお下品に。お好きな方をどうぞ
LoRA merged into v14.0. A little more vulgar than 14.0. Choose whichever you prefer.
v14.0
使用モデルを一部変更。LoRA未使用でリアルさ維持したつもり
下品な感じは控えめになっていると思います
Some changes were made to the model used. LoRA was not used, and the aim was to maintain realism.I think the vulgarity has been toned down.
v9.0～
コスプレっ子もリアルにを目指してみた。CFGスケール4ぐらいがいいかも
I tried to make the cosplayers look more realistic. CFG scale 4 might be good.
v8.0
エロ強化したつもり
I thought I'd made it more erotic.
v3.0～v3.6、v4.0～v6.0、v7.0～v7.3
日本人っぽく、リアルさ重視のつもり。DMD2付きはDMD2のLoRAをマージ
I wanted to make it look Japanese and realistic. DMD2 version merges LoRA with DMD2
v1.0
初版
first edition
Description
アニメ調のモデルを追加
少しプロンプトに素直になった・・・と思う
※LoRAはマージしていません
Added anime-style models
I think it's a bit more responsive to the prompts...
※Not merging LoRA
FAQ
Comments (7)
AIコスプレ用にずっと1.4を使っていたのですが、3.0良さげですね（スケージューラーが限られる感じがありますが）
I've loved the Kodora models since day one, however I don't know what happened between v3.0 and the previous version, but v3.0 consistantly generates blurry and blocky images. Hair especially no longer looks realistic and instead looks like painted plastic shells. Compared to pre-v3.0 images using the same prompt and settings (even in the sample images,) the older versions looked beautiful and all the v3.0 results look like poorly-compressed .jpg images. :(
Thank you. This may be due to the addition of anime-style models. I'm sorry, but please use the old version or the one you prefer.
※google translation
I'm not sure if it will meet your expectations, but I've also uploaded the version before I added the anime-style model. (v2.5)
※google translation
Thanks for the upload of 2.5. It does seem to suffer from the same issues as 3.0, though not to as such an extreme level. I've posted an image comparing the last four versions using the same prompts/settings/seed. You can see that skin textures, hair, and even lighting, seemed to peek with 2.1LH. Then something happened with 2.5 that got even worse with 3.0.
In that case, it's possible that this is due to the influence of other models that were added.
I can't promise that it will be improved in the next version, but I'll take your information into consideration.Thank you.
※google translation
v3.1 is looking good, doesn't seem to have the problems the last couple versions did. :)