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
Retrained against my Tweaked Base Pony XL checkpoint (to allow for some subtle quality improvements) on a dataset with around 200 more images than V3's. The whole dataset was also recaptioned from the ground up using the same combined "Florence 2 Large detailed captions + WD-VIT-3 Booru tags" approach I've been using elsewhere recently.
This version no longer uses a unique trigger, instead being trained directly against 'source_anime'. Using '2d' in the positive and '3d, cgi' in the negative will also tend to strengthen the effect. Recommended strength is around 0.7 - 0.8.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.