SDXL LoRA/LyCORIS works best on its original training model. You may need to reduce weight when using it with other models or additional LoRAs.
LyCORIS Combination Recommendation: Try using four of my LyCORIS models with the following weights: 0.4, 0.3, 0.2, 0.2 (or any combination with a total weight around 1.0).
I will release multiple versions for a few popular models. Feel free to request for artist or model.
Version naming convention: MajorVersion.MinorVersion [BaseModel]
MajorVesion: For big updates that can apply to any style LoRA. For example, training parameter update.
MinorVersion: For small updates that only apply to this LoRA. For example, epoch selection, removing a certain image from dataset.
BaseModel: SDXL LoRA/LyCORIS works best on the model that it was trained on.
Description
FAQ
Comments (6)
How do we find the exact prompts for characters and character outfits?
I would like to know if you can help me.
Look for the character on danbooru and check how people tagged the character.
I think the LAM model is a difficult artist model to use and the results are quite bad, and it looks like a general AI image. 😅
Hi, thank you for your feedback. You may right-click on one of my demo images, open in new tab and download the original image with generation metadata. You can let WebUI loads my generation configuration and see if my configuration works for you.
From what I have observed, all versions of the model do not reproduce the style of LAM very well. The lighting and colors are not the same as the original artist's. The anatomy also looks strange, unlike other artists who are almost the same as the original. I guess the current models do not reproduce the style of LAM very well.
@NOAIOKOKOKOK Thanks for testing this out. Will try making a V-pred one with V6 training strategy.