AutismMix (DPO version) merged with of 2.5d style lora (with 0.6 weight). All credits to authors of combined models.
This combination has similar (in my point of view) style to my favorite 2.5d checkpoints of sd1.5.
I'm using this checkpoint for most of my images right now, including those I plan to upload, so might as well post it I guess.
PS:
I've created it when there weren't many checkpoints for ponyXL available yet and it didn't even have its own category in civit. I personally use Incursio's checkpoint nowadays for 2.5d stuff and I think I can recommend it. I can also recommend the VividPDXL checkpoint.
But feel free to use this simple mix if you like it, it's not going anywhere.
PS2:
Also, after almost dropping it, I've recently ?????????????? again and even uploaded a new version. It's still decent compared to checkpoints mentioned above when you want to push autismMix's style slightly to 2.5D, have a lot of spare disk space and don't want to use loras for style. Keep in mind that it doesn't bring that much value compared to just using the lora and you actually lose its flexibility.
Same as previous version but with 2.5DCartoonV2 instead of the 2.5DCartoon.
Overall, it has slighter effect (just like original lora applied with same weight) than previous version. Depending on your taste or particular case, might perform better or worse than previous merge.
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
