Lora模型使用介绍

Celestine Lucullus

2023/2/25 update Prune tags to make the description more accurate. Adjust rank to 32 to balance file size and quality.

Introduction A LORA model of Celestine Lucullus from Kuroinu. The 784mb VAEs (NAI, Orangemix, Anything, Counterfeit) are recommended. 0.6~0.8 weights are good. It‘s recommended to use with any olga discordia LORA to generate high-quality nsfw masterpiece. The preview images are generated using latest version of YesMix.

Adventurers

Thank you all for downloading and reviewing this LoRA! I currently have plans to work on the next version, but there are still many challenges to overcome.

In addition, I found that sometimes certain themes can work better as standalone LoRAs rather than mixed LoRAs. As a pre-practice for the updated version, I have created some standalone LoRAs, including:

Angelic Wairrors For divine armored characters such as Valkyrie, Priestesses, Paladin, Knight, and Angel.

Not Horny Pirate For classic pirate.

Norse Viking For Nordic style Viking Warrior and Berserker.

Non-Hentai Elf For traditional fantasy elf characters such as Ranger, Warrior, Druid, and Priestess.

Thank you once again for your patience and support!

Hipoly 3D Model

High-poly 3D Model LoRA This is a LoRA trained on high-polygon 3D model images.

It can provide clean, high-resolution skin and hair materials, as well as detailed clothing elements.

For those interested, I have compiled the technical insights gained during the training of ver.2 in the following article.

https://note.com/takumi__ncr/n/n21016c358ea5

Changes in 2.0 Increased the number of training images

Increased the training resolution (ver.1: 768, ver.2: 896)

Revised the tagging

Removed the trigger word as well

Reviewed the training parameters

Improvements in 2.0 It can reproduce a more 3D-like texture and stereoscopi effect than ver.1

LoRA can be applied without a trigger word

The style can be controlled using 3d and realistic tags

When added to Positive Prompt, it enhances the 3D feel

When added to Negative Prompt, it adds details such as clothing while maintaining the model's art style

The issue of eroding the model's art style with tags such as intricate, detailed has been alleviated

Additional information The effect of LoRA was confirmed using the following my custom merged models:

Alstroemeria Mix

Bougainvillea Mix

Chrysanthemum Mix

High-poly 3D Model LoRA ハイポリゴン 3D モデル画像を学習した LoRA です。

3D らしいクリーンで高精細な肌・髪の質感や、衣服のディテールを与えることができます。

ver.2 の学習時に得られた技術的知見をまとめましたので、興味がある方は次の記事をご覧ください。

https://note.com/takumi__ncr/n/n2fb9d265ffa9

2.0 での変更点教師画像を増やしました

学習解像度を向上しました (ver.1: 768, ver.2: 896)

タグ付けを見直しました

トリガーワードも削除しました

学習パラメータを見直しました

2.0 での改善点 ver.1 よりも 3D らしいテクスチャ感、奥行き感が再現できます

トリガーワードなしで LoRA を適用することが可能です

3d, realistic タグを使用することで絵柄のコントロールが可能です

Positive Prompt に入れた場合、より 3D 感を強化します

Negative Prompt に入れた場合、モデルの絵柄を保ちつつ、衣装などのディテールを追加することができます

intricate, detailed などのタグによってモデルの絵柄を侵食してしまう問題が緩和されました

その他 LoRA の動作確認は以下の自作マージモデルを使用して行いました。

Alstroemeria Mix

Bougainvillea Mix

Chrysanthemum Mix

Thai university

This Lora made for make the White shirt and Black skirt near to female thailand uniform

BASE model train from Chilloutmix ni

Use: black skirt for normal university skirt

but if you want the tight one i suggest black tight skirt or black pencil skirt