Recently updated on 12 6 月, 2023 at 04:59 上午
以下作者原文：
Description
This is a merge of some random anime based and cartoon based models to achieve a somewhat cartoony anime style, more similar to what you would actually see in anime as opposed to the more common hyper-detailed anime models.
(note - you won't be able to replicate the sample images precisely, I use a custom noise generation algorithm in my setup, so the seeds would be interpreted in a different way. This doesn't affect the quality whatsoever though)
Usage Guide
(highly recommended) Use the dynamic thresholding plugin: https://github.com/mcmonkeyprojects/sd-dynamic-thresholding
Set the config scale to 13.5
Click the checkbox "Enable Dynamic Thresholding (CFG Scale Fix)"
Set the Mimic CFG Scale to 4.5
For an alternative style, set config scale to 15.5 and Mimic CFG scale to 9.0
(highly recommended) Use a negative embedding for best results
I use verybadimagenegative_v1.3 and easynegative (all examples use this)
verybadimagenegative_v1.3
https://civitai.com/models/11772/verybadimagenegative
easynegative
https://civitai.com/models/7808/easynegative
Place the downloaded files into the "embeddings" folder of the SD WebUI
In the negative prompt, paste "verybadimagenegative_v1.3, easynegative"
This merge is very easy to prompt, and does not require a ton of prompt engineering to get good results. The following format will yield decent results:
Prompt:
(best-quality:0.8), perfect anime illustration, <normal description of the image, e.g. a woman running in tokyo at night, a flaming meteor, etc.>
Negative:
(worst quality:0.8), verybadimagenegative_v1.3, easynegative, (surreal:0.8), (modernism:0.8), (art deco:0.8), (art nouveau:0.8)
Upscaling at 2x using R-ESRGAN 4x+ Anime6B works very well (no need for high weights, 0.45 will work fine)
The model is capable of NSFW
原文链接：https://cj.suclub.top/3494.html，转载请注明出处。
请先 ！