[Will be retraining for Anime Preview V2 in the next few days expanding dataset]

A D3monOne style lora for Anima Preview ONLY this will not work as intended on any other model.

Generation Settings:

[Please note in the samples I have not used High Res Fix or Facedetailer this is the expect result before needing to do any post processing/passes.]

What was used to gen the above images.

• Sampler: er_sde

• Scheduler: simple

• Steps: 30

• Resolutions: Any 1024x resolution will work just fine.
  My preferred resolutions: [896 x 1152, 1152 x 896, 832x1216, 1216x832, 1344x768, 768x1344]

• CFG: 5 (4-5)

Very happy with how this turned out, I may do some fine tuning on it when I get the time and chance to.

Triggerword: d3z1d2
Lora Strength: 1.0 - 0.9 but can go a little lower if you like.

More than happy to hear and see some feedback. Happy genning!

Updates:

v1.1 - Adjusted Dim/Alpha for much more stable faces and some details.