SDXL LoRA/LyCORIS works best on the model that it was trained on. 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 (5)
can it be possible to train a style lora on this artist ? theobrobine
HI, I probably won't make one as most of the datasets are videos and GIFs.
oh @silvermoong i searched through kemono and found artist drive link https://drive.google.com/drive/folders/1xdSfErzxoVFjdYVge1jw2cSeZpg_0LG6 it has frame by frame images of his animation, can the be used somehow?
@ACSAI Hi, I took a glance at this dataset. Most of them are characters with transparent backgrounds. I can extract frames from GIFs. However, most of the GIFs don't have high resolutions.
In short, it will be a large amount of work, but the result won't necessarily be good.
@silvermoong oh is that so, i wasn't aware about that, thanks for taking your time