I don't speak English so I'm translating at ChatGPT. Let me know if the English is weird.
This is the Noob version of Featureless 2.5D Mix.
I recommend using the "realistic" tag.
(about half of the sample images were generated using the "realistic" tag).
Additionally, when characters are depicted from a distance, their eyes may become blurred.
In such cases, try using hires fix (latent) or similar methods to address the issue.
Featureless 2.5D MixのNoob版です。
realisticタグがおすすめです。(サンプル画像の半分ぐらいにrealisticタグを利用しています)
また、人物の描写が遠くなると目がつぶれやすいので、
その場合はhires fix(latent)などで対策してください。
Training Image Breakdown / 教師画像内訳
I used the AnyIllustrious-XL(for LoRA training) as the pretrained model
and conducted additional training with the following images.
pretrained modelにAnyIllustrious-XL(for LoRA training)を使用し、
以下の画像を使い追加学習しました。
Featureless 2.5D Mix 1000 images (white background)
Version history
V1
merge model ( merge ratio : model name )
0.5 : NoobAI-XL Epsilon-pred 1.1-Version https://civarchive.com/models/833294?modelVersionId=1116447
0.1 : Alchemist Mix v4.0 https://civarchive.com/models/1030120?modelVersionId=1227613
0.1 : MonsterCoffeeC4! Mix v1.0 https://civarchive.com/models/1029855?modelVersionId=1155120
0.1 : vall mix semi realism/2.5d v3.8 https://civarchive.com/models/1033829?modelVersionId=1222667
0.1 : CyberIllustrious v1.0 https://civarchive.com/models/1125067?modelVersionId=1264546
0.1 : Featureless Mix Illustrious v1.5 https://civarchive.com/models/954005?modelVersionId=1138496
merge LoRA : trained LoRA (0.6)
merge VAE : XL_VAE_C F1
V2
All of the following models are merged so that they are all in the same proportion
以下のモデルをすべて同じ割合になるようマージberet mix 3D v1.0 https://civarchive.com/models/1557570?modelVersionId=1762552
Creativitij v1.0 https://civarchive.com/models/1398870?modelVersionId=1581191
Diving-Illustrious Anime v9.0 https://civarchive.com/models/1170176?modelVersionId=1635459
DucHaiten-NoobAI-Cinematic v1.0 https://civarchive.com/models/1546201?modelVersionId=1762133
Uncanny Animal - 0.5 v1.0 https://civarchive.com/models/1411367?modelVersionId=1595499
Featureless 2.5D Mix Noob v1.0
merge VAE : XL_VAE_C F2-2
V3
All of the following models are merged so that they are all in the same proportion
以下のモデルをすべて同じ割合になるようマージCyberRealistic CyberIllustrious Semi-Realistic Illust_Semi-Real v1.0 https://civarchive.com/models/1991867?modelVersionId=2254636
uncAni SFW/NSFW v4.0 https://civarchive.com/models/1710752?modelVersionId=2123587
injoij v1 https://civarchive.com/models/2040478?modelVersionId=2309521
Featureless 2.5D Mix Noob v2.0
merge VAE : XL_VAE_C F2-2
License
This model is merged with a model based on NoobAI-XL and therefore inherits the Fair AI Public License 1.0-SD. Additionally, unique restrictions have been added in NoobAI-XL. For more details, please refer to the license section of NoobAI-XL.
The license icons displayed on the right side of this page reflect the content of the above-mentioned license. In case of any discrepancies between the above-mentioned license and the license icons on the right side of this page, the content of the above-mentioned license takes precedence.
このモデルはNoobAI-XLをベースとするモデルをマージしているため、Fair AI Public License 1.0-SDを継承しています。また、NoobAI-XLにて独自の制約が追加されています。詳細はNoobAI-XLのライセンス項を参照ください。
本ページの右側に記載されているライセンスに関するアイコンの表記は上記ライセンスの内容を反映しているものです。上記ライセンスと本ページ右側のライセンスアイコンに差異がある場合、上記ライセンスの内容が優先されます。