LoCon trained on GreatestGori's artstyle for ponydiff: https://civitai.com/models/257749
Artist: https://www.pixiv.net/en/users/80678191
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
The scheduler used is Karras
I've been playing around with the Align Your Steps scheduler and it seems to be working well, while the samples aren't made with it it's something to look into
Initial resolution is selected from the SDXL whitepaper appendix I: https://arxiv.org/pdf/2307.01952
Perturbed Attention Guidance is used for the initial image
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-.45 denoise
A facedetailer is used
I use ComfyUI, sorry
What strength should I be using?
~ .8 - 1
Sample images Model?
A mix of 60% Autimmix Confetti, 40% PonyFaetality V11
I recommend using a merge at this point, Autismmix confetti is my primary but there are plenty of good ones
Important note is that for this one I was too lazy to do trials on base pony, whoops
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