Type | |
Stats | 782 34,545 30.9k |
Reviews | (105) |
Published | Jul 1, 2024 |
Base Model | |
Training | Epochs: 30 |
Usage Tips | Clip Skip: 2 |
Hash | AutoV2 6B7EFC3CC4 |
LoCon trained on Fiz-Rot's artstyle for ponydiff: https://civitai.com/models/257749
Artist: He's back but his new stuff isn't making it into my dataset, find him yourself on Pixiv
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.
If you need it for some reason the (old) standard LoRA version exists here: https://civitai.com/models/288465
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
21.1 The scheduler is Karras
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 denoise
A facedetailer is used
I use ComfyUI, sorry
What strength should I be using?
Base Pony: .9 - 1
AutismMix: 1
21.1 I recommend Autism_Confetti at .8-1 strength, or <.8 if mixing with other resources
I absolutely recommend finding a merge at this point, Autismmix Confetti is my go-to but there are plenty of good ones like ponyFaetality or cashmoneyAnime
Pairs of images?
Left image is AutismMix, Right image is base Pony
21.1 All images are AutismMix Confetti
Why not put this as a version on the existing model?
As far as I'm aware civit does not allow me to independently tag standard LoRA versions and LyCORIS versions on the same model page, so I've separated them to reflect this.
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
This sucks
God as my witness I'll make it good one day
God as my witness I think it's good now
God as my witness It's firmly mid