Introduction

This is the SDXL version of Celestine Lucullus LoRA/Lycoris. Do not use it with any SD1.5 model. The dataset is classified using rating tags: safe, general, sensitive, nsfw, questionable, explicit, which can control the results.

Generating Settings

• Sampler: DPM++ samplers, Euler a are recommended.

• Eta noise delta: 31337 or 0

• Upscale Method: HiresFix+4xAnimeSharp

• Max Resolution without Upscaling: 1024x1024

• VAE: No need to use external VAEs.

• Embeddings: Technically no need to load any external embeddings to enhance quality, but negativeXL is recommended.

• Clip Skip: 1 (SDXL model does not support clip skip).

• Weights: 0.6~1 are recommended (AnimagineXL may contain prior knowledge about this character, the 'oversaturation' effect of generated images can be alleviated by appropriately reducing weights of LoRA/Lycoris).