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.
Change notes:
v2.233->v2.233-2: Switching to a new epoch selecting strategy: reducing overfitting and improving hands.
Description
FAQ
Comments (6)
A masterpiece, I feel that the lora you made has found a balance between overfitting and flexibility. I don’t know if it’s because you found some new training techniques or the new base model, but it’s really amazing.
Thanks for your support!
This lora is amazing. My only gripe is that I wish I could tag by character name for the rpg characters.
It looks good but every image generated ends up looking more all blurry no matter what Lora I use. Any solution?
me too
I am not sure, but I found that I cannot directly search this lora, your other Takeda Hiromitsu loras are all fine, just this one cannot. strange thing.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.