My first attempt at making LoRA's, So if its shit, I'm sorry.
I tried to include as much as possible, but your mileage may (will) vary, especially which model you decide you use. Semi realistic models tend to produce images that are very close to source material. You will have to play around with the tags a bunch to get what you want, its is very sensitive.
Often times its not enough to just say the character's name, you have to describe what they look like, so for example: "Doll, worker drone, dress, orange eyes, glowing eyes, helmet, purple hair," etcetera...
Over all, I'm proud that this even worked at all and the images look legible, let alone presentable.. to an audience of one. and with limited testing, it seems to play nicely with other LoRA's.
Also, you might notice that some character are easier to reproduce than others you might notice that those harder to reproduce characters also appear less on screen, this is not coincidence.
Psst... If you want to make Tessa, make sure you use silhouette in your prompt!
Will (maybe) add upon later if i remember.
Added more images
Better tagging (???)
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
