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 (10)
Thanks for the model🤍
Can you please tell me did you trained all images or only latest images? Because as I can see only latest images results only, this artist old style and sketch are too good
I only used latest images
@silvermoong please create on old style. also old style is far better than latest
@itachiii There are multiple reasons that I only use latest images. I will think about this.
Heyoo, I would like to request a style? If that's possible ofc.
I want a style made from this person right here - https://x.com/usloprk
@Cosmosmji Added to list. Please note that I currently have a very long wait list. This will take a while.
能否请作者大大制作oohira sunset画师(https://www.pixiv.net/users/4872)的风格？非常感谢！
底模是illustrious的话就完美了，谢谢😄
@icelook4f749 感觉图片数量可能不够，我有使用过黑白漫画的测试，但是好像效果不太好
@silvermoong 好的☺