LoRA trained on WamuDraws' artstyle for ponydiff: https://civitai.com/models/257749
Artist: https://x.com/wamudraws
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 768 x 1152 or vice-versa and upscaled by x(5/3), 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?
For base pony between .8 - 1, I recommend .8 if you do an upscale pass
For AutismMix_pony (https://civitai.com/models/288584), 1 performs well, this merge performs pretty well and I'll likely use it for the images going forward. Around half the sample images are with this mix, I leave you to guess which ones
Trigger word?
No