This model's fairly good at achieving a Play-doh/claymation-esque look to your videos. It's especially great when used in tandem with my FLUX LoRA for I2V workflows (Link to that here: https://civitai.com/models/1358040/claydoh?modelVersionId=1534108). I highly recommend generating imagery using that, and then using this LoRA to generate your motion for the best effects. I may update this LoRA over time if I manage to increase its quality. Keep in mind this is for Wan 2.1 14B. Thanks for your support!
I may update this model over time if I learn to improve it, however, this was the best epoch I found in my training results. I have a 1.3B version as well, but am still determining which is best from my training results in that regard.
1. Dieses Modell dient nur Lernzwecken. Urheber- und Auslegungsrechte liegen beim Originalautor.
2. Bist du der Originalautor eines Modells, kontaktiere uns bitte zur Authentifizierung über unsere offiziellen Kanäle. Wir schützen die Rechte aller Schöpfer. Hier klicken, um es zu verifizieren.
