LoCon trained on Vammzu's artstyle for ponydiff: https://civitai.com/models/257749
Artist: https://twitter.com/vammzu
Because of my lack of experience and time, the version number may be based on changes that have made certain aspects worse. As such a previous version may perform better than a later version.
I'm still learning the ins and outs of the model and LoRA training in general, please leave reproducible feedback or tips so that I may improve over time.
Check the "About this version" section for any quirks or pitfalls I'm aware of or have experienced.
Some Q's:
What's your workflow?
Sampler from images is done with Restarts with segments of [3,2,0.06,0.30], which are values from the paper on Restarts
Initial resolution is typically 832 x 1248 or vice-versa and upscaled by x(20/13), I try to keep the pixel count around 1024 x 1024 for initial gens and adjust the upscale ratio as needed
Upscaler is usually 4x_fatal_Anime_500000_G or 4x_NMKD-Siax_200k
Second sample pass is the same as the first (params are on civit's meta interface) but at ~.35 denoise
A facedetailer is used
I use ComfyUI, sorry
What strength should I be using?
.8 - 1 on both base and merges
If it's too strong use .8
Pairs of images?
Left image is AutismMix, Right image is base Pony
What does your filename structure mean?
It's split into 4 parts of [XX]-MAnon-[YYYY]-[ZZZZZZ]
[XX] - Artist initials
MAnon - My moniker
[YYYY] - SD version and Model version (Ex. XLV4.1 is on SDXL [Not 1.5] and it's version 4.1 of the model)
[ZZZZZZ] - The epochs, only useful to me