Preview images do not use other LoRAs.

(I've only tried it with base Pony so far, Civitai was slow and unstable today so I wasn't in the mood to look up recommendations for those)

❌💲 Commercial use of this model is not allowed

My worst Pony LoRA so far. I had a bad feeling but did it anyway because... reasons. This is the first time I train a LoRA for two characters, at least they look mostly identical... Thomas was sort of a guinea pig for me before I'd try these characters.

Negatives I use a lot: human, cropped face, another locomotive, passenger coach, goods wagon, no tender /(rail vehicle/), snow, buried in snow, snow pile in front, snowplow

Wait, which direction do the slashes go?..

DATASET

I gathered 135 images but there are many elements I TRY to leave out and some repeating scenes. I'm already considering an alternate version that would be less annoying. Maybe, it's getting close to 2 AM here and I can't think straight...

Most images are from episodes Love Me Tender and Emily in the Middle (the only 2 CGI episodes with Donald and Douglas having lead roles), smaller portion is from feature film Sodor's Legend of the Lost Treasure, and a few other images.

I chose to AVOID pictures showing complex formations (Donald + coach + Douglas, tenderless Douglas + Donald + coach + Douglas' tender), the dataset was deranged enough without those...

I tagged their features but it really doesn't matter.

ISSUES

This LoRA is a trainwreck in general, only suitable for shitpost-tier results.