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 3 of my LyCORIS models with the following weights: 0.5, 0.4, 0.3 (or any combination with a total weight around 1-1.2).
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)
Create this artstyle
@itachiii Added to list for now. I'm aiming for around 100 images, will do some more searching once it’s his/her turn.
Why aren't you using the latest models like Illustrious-XL 1.0, 1.1, and 2.0 for training?
Hi @Nowaks11 I previously tested Illustrious 1.0, but it wasn't good. I’ve been reconsidering my choice of base models, as capability is a major factor for LoRA training. Currently, I use Illustrious 0.1 for E-pred and Noob VP 1.0 for V-pred by default, but I’m open to discussing other model options
Finally you make it! Which base model are you using for these images? My results never have the same vibrant colors as yours
@MoonLightBeast Hi, I simply use Illustrious v0.1. You can right-click on any of my demo images, open in new tab and download the original image with generation metadata.
@silvermoong Thanks for your help! Could you provide the prompts you used to generate the base images for the LoRA? I’m looking to recreate all of this author's images!
@MoonLightBeast Just use WD14
@silvermoong thank you
Can you consider doing qqqpppqpqpqp二号机 lora?
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.