User LoRA

XL

【Art Style】Soyincapazz Style (For SDXL)

【Art Style】Soyincapazz Style (For SDXL) - AI Model cover image
Uploaded at
Apr 27, 2024, 10:50 PM
Uses
3.4k
Reviews
Good  (3)
Trigger Words

【Art Style】Soyincapazz Style (For SDXL)V1.0,

Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Description

https://civitai.com/models/423523?modelVersionId=471877

Introduction This is the SDXL version of Soyincapazz Style LoRA/Lycoris. Do not use it with any SD1.5 model. The dataset is tagged using the latest version of WD-14 Tagger V3 and classified using rating tags: safe, 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: 0.6~0.8 are recommended.

Comments1

Artwork made by 【Art Style】Soyincapazz Style (For SDXL)