weight: 0.7-1.3 as you like. Below 0.7 may lead to situations where the composition may be damaged.
It is recommended to use 2D checkpoints, such as AOM, Anything and so on.
Since it is a background image, the training set contains almost no humans or other animals, so it is not sure how they will be drawn when specified.
trigger words: most of them include no_humans, scenery, but also fine without them.
The images in the training set are all horizontal compositions, so plotting of vertical compositions may encounter some problems.
1. Modèle partagé uniquement à l'apprentissage et au partage. Droits d'auteur et interprétation finale réservés à l'auteur original.
2. Auteur souhaitant revendiquer le modèle : Contactez officiellement SeaArt AI pour l'authentification. Nous protégeons les droits de chaque auteur. Cliquer pour revendiquer
