Dettagli
Raccomandazioni
v1.0
Blood and Spirit Mix

Blood and Spirit Mix

22.3K
164
236
#guy
#Style
#woman
#illustration style

Blood and Spirit Mix V1.0

My second model is not an anime model, but an illustration model.

The biggest feature is that it is designed not only for girls but also for guys. It is also designed to be used as illustrations for novels, etc.

第2弾はアニメ系ではなく,イラスト系のモデルとなります。

最大の特徴は女の子だけではなく男も出すことを考慮したものになっていることです。また,小説の挿絵などで使うことを想定して構成しています。

As you can easily see by looking at the picture, we have mainly merged models for ladies. I don't think many men have ever used it, but compared to regular models, it is characterized by a completely different sense of distance between men and women. While retaining that feel, I arranged the characters and designs to appeal to the general public, and adjusted them so that they can be used in many situations.

絵を見ればすぐにわかりますが,女性向けのモデルをメインでマージしています。多くの男性はあまり使ったことがないだろうと思いますが,一般のモデルと比べると男女の距離感がまったく違うのが特徴です。そういった風合いは残しつつキャラや絵柄を一般向けにアレンジし,多くのシチュエーションで使えるように調整しました。

The recommended CFG Scale is 5 to 6, or even 4 in some cases.

CFG Scaleの推奨は5~6,場合によっては4くらいです。

There is no need to use the detail type Lora, and the model has a lot of lines, so normal output does not produce a stable picture. Once you have decided on the general composition, apply HiRes.Fix. Denoising strength is recommended to be around 0.4. If you experience burning, use lower the CFG scale.

 detail系のLoraを使うまでもなく非常に線の多いモデルとなっており,通常の出力では??した絵はあまり出てきません。だいたいの構図が決まったらHiRes.Fixをかけてください。Denoising strengthは0.4くらいが推奨です。焼けが出るようならCFG scaleを下げてください。

If the face is unstable, you should use a negative embedding such as easynegative. However, the picture changes drastically. All examples use easynegative. If you want to leave a fluffy feel, I recommend fastnegative.

 顔が??しないようならeasynegativeなどのnegative embeddingを使うといいでしょう。ただし,極端に絵が変わります。ふわふわ感を残したいならfastnegativeをお勧めします。作例ではすべてeasynegativeを使っています。

Visualizza la traduzione

Valutazioni e recensioni

5.0 /5
0 valutazioni

Non ancora ricevute valutazioni o commenti sufficienti

A
Annuncio
2024-04-01
Pubblicare modello
2023-11-21
Aggiorna le informazioni del modello
Dettagli modello
Tipo
Checkpoint
Data di pubblicazione
2023-11-21
Modello Base
SD 1.5
Ambito di Licenza
Model Source: civitai

1. I diritti dei modelli ripubblicati appartengono ai creatori originali.

2. I creatori originali che desiderano reclamare il proprio modello devono contattare il personale di SeaArt AI tramite canali ufficiali. Clicca per rivendicare

Ambito di Licenza di Creazione
Immagini Online
Effettua una Fusione
Consenti Download
Licenza Commerciale
Le immagini generate possono essere vendute o utilizzate per scopi commerciali
Consenti la rivendita del modello o la vendita dopo la fusione
QR Code
Scarica l'app SeaArt
Continua il tuo viaggio di creazione AI su mobile