LostPhynotype5 Style V1.1
Retrained using 2,000 reg images that greatly improve style adherence. Trained on base pony, but new favorite checkpoint for this LoRA is SweetMixPony
LostPhynotype5 Style v1.0(outdated)
Pony LoRA trained on art by LostPhynotype5. Pretty niche style and artist that may not to be everyone's liking, but offers a distinct painting style.
PARAMETERS
Weight 0.85-1.0 will generate closest to his style
Weight 0.3-0.7 will still have a great output, but less painting/gritty style and smoother.
Triggers: PHYN0TYP35, painting
Pony tag source_cartoon can help, although not necessary.
I recommend using adetailer(A1111)/facedetailer(comfy) at a higher denoise than you'd be used to, I personally use 0.5. Faces just tend to suffer the most due to the art style, and how AI trains on a dataset.
!!SHAMELESS SELF SHILLING!!
Appreciate what I do? Here's a few ways to support me <3
Give me some gas money on PayPal
Description
Same dataset, except i used 2,000 reg images that I believe help with getting a cleaner and more consistent style. Still trained on Base Pony.
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.