大家好，我是chosen鲷，这次带来的是snatti原画风格lora。
snatti是以为我很喜欢的瑞典艺术家，之前专门训练过他的小柯基lora，这个是他的画风模型，是那种比较典型的原画风格。
这个lora可以作为风格挂件使用，但是权重别太大，0.7顶天了，作为挂件的话0.40.5什么的就可以了。触发词：style bysnatti
推荐的tag：
style by snatti,
这里写你想要的内容
<lora:style by snatti-000018:0.9>
Negative prompt: EasyNegative, badhandsv5-neg,Subtitles,word,
Steps: 32, Sampler: DPM++ SDE Karras, CFG scale: 7, Seed: 2233620323, Size: 512x768, Model hash: 52b8ebbd5b, Model: chosen-mix bake vae, Denoising strength: 0.5, Clip skip: 2, ADetailer model: mediapipe_face_full, ADetailer confidence: 0.3, ADetailer dilate/erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer version: 23.6.1.post0, Hires upscale: 2, Hires steps: 12, Hires upscaler: R-ESRGAN 4x+ Anime6B, Lora hashes: "style by snatti-000018: fce27a010533", Version: v1.4.1
大模型我推荐用我的chosen mix（就是下方推荐里第一个），其他的常见模型也都可以，这模型的兼容性还不错，但是推荐用厚涂画风的二次元插画模型.
The following content is from Google Translate
Hello everyone, I am Chosen Roach, and this time I bring you Lora the style by Snatti .
Snatti is a Swedish artist that I really admire. I previously trained a model called "Little Corgi Lora" in his style, and this model represents his typical original art style.
Lora in the Snatti original art style can be used as a decorative piece with a specific style. However, please don't set the weight too high. 0.7 is the maximum value, and for decorative purposes, 0.4 or 0.5 would be sufficient. Trigger phrase: style by snatti
Recommended tags:
style by snatti
Please write down the content you want.
<lora:style by snatti-000018:0.9> Negative prompt: EasyNegative, badhandsv5-neg, Subtitles, word Steps: 32, Sampler: DPM++ SDE Karras, CFG scale: 7, Seed: 2233620323, Size: 512x768, Model hash: 52b8ebbd5b, Model: Chosen Mix Bake VAE, Denoising strength: 0.5, Clip skip: 2, ADetailer model: mediapipe_face_full, ADetailer confidence: 0.3, ADetailer dilate/erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer version: 23.6.1.post0, Hires upscale: 2, Hires steps: 12, Hires upscaler: R-ESRGAN 4x+ Anime6B Lora hashes: "style by snatti-000018: fce27a010533" Version: v1.4.1
For the large model, I recommend using my Chosen Mix (the first one in the recommended models below). Other common models can also be used as this model has good compatibility. However, I suggest using a two-dimensional illustration model with a thick paint style.
Thank you all for downloading and using my models. If you like them, please feel free to follow me. My Bilibili and Pixiv IDs are both Chosen Roach. You are welcome to check out my channels at https://space.bilibili.com/3867754?spm_id_from=333.1007.0.0 and https://www.pixiv.net/users/40911695. Thank you.
