Update: V2_DMD2 is a V2 with the DMD2 Speed LoRA included + a custom LoRA to fix contrast and hands. You can use it without the Speed LoRA:
Lower your CFG to 1.2~1.4 (for original effect), ~2.5 for what i feel is a nice result.
Switch to Euler A+Auto or LCM+Normal
~8 steps (both for normal and hires)
Small update: Thanks to clueless_engineer i realized that this model can do GREAT stuff leveraging the DMD2 speed LoRA with low step count! Check the pinned pictures!
This model is an attempt at "fixing" just enough the base Illustrious models to help me training/tests LoRA without too much influence.
To do so, i have done a merge of Illustrious + one of my models at 0.15, CosineB calculation mode.
v0.1 is Illustrious v0.1 + AnBan AlterV3
v2.0 is Illustrious v2.0 stable + AnBan ShinV1
It's really more of a personal test than a real "let's all do this now" š
Description
FAQ
Comments (9)
if I train with this, would the lora be compatible with other checkpoints?
Normally, yes, but i haven't finished experimenting with it. Most of the time, training with WAI is a safer bet for Illustrious
n_ArnoĀ Is there a tutorial on how to train a lora with wai or other checkpoint?
diego892009410Ā There is quite a few available as article here at civitai, i'll link you one
diego892009410Ā https://civitai.com/articles/18006
n_ArnoĀ wai. hmm. experimentation time šā
As soon as I saw the first image I generated, I added this model to my favorites list.
None of the ~50 images I posted to your model's gallery used ADetailer. The eyes/face came out great as-is.
For some reason v2 is missing a hash, so any images generated and uploaded to civitai will not auto-detect the model.
Argh, thanks for letting me know! I'll check and see if i can fix this