This training data has Absolutely no logo, text and watermarks at all, and cannot always generates anime arts.

Recommended settings:

• Sampler: Euler a, DPM++ 2M Karras

• Sampling Steps: 20+

• CFG Scale: 3-7

Recommended tags:

• Use source_anime for a better result (when generating pony images)

I hope you enjoy using this LoRa Model. By the way, don't forget to follow me on social medias!