This lora was trained on 50-185 images from the artwork of Musouzuki. If you enjoy their work I encourage you to support them on their social media pages. The pony version isn’t a perfect re-creation. It has problems with hands and feet. The backgrounds on both loras leave a lot to be desired. I believe this is mostly due to the dataset. Despite this, both versions mimics the “core concept” of the artist’s style well enough.
To get the results you see in the images above, these are the settings I used.
V3: Trained on Anima 1.0.
Version 2.0 was trained on Noob 1.0 V-Pred.
Version 1.0 was trained on Autism Pony. I haven’t tested it with anything else.



