DoRA is trained on the style from the game Zenless Zone Zero.
DoRA weight: I recommend using the DoRA weight between 0.7 and 0.85. I personally use 0.85.
Recommended model: DoRA was trained on the AnimagineXLV3.1&4 model, so I recommend using it.
Clip skip: The clip skip of the DoRA is 2, just as specified for the AnimagineXLV3.1&4 model.
When writing a prompt, I recommend following the guidelines that are specified for AnimagineXLV3.1&4.
Description
- Expanded dataset
- Trained on a slightly smaller number of epochs
- This version is not necessarily better than 1.0. But for me, version 2.0 is better than 1.0.