A Pony Diffusion V6 style Lora trained on a diverse dataset of people-free (so as not to interfere with base Pony pose knowledge) high-quality AAM XL generations, with equal bucket image counts for 1024x1024, 1216x832, and 832x1216.
See the "about this version" section of the page for more detailed information on any particular version of the Lora.
Description
Added around another 60 images to the dataset to fill out a few more stylistic "gaps". Cleaned up / improved captions on certain existing images. Retrained a bit more thoroughly, with the added bonus that resolution bucketing for XL / Pony is now working properly in the CivitAI online trainer.