📢 登入問題已解決 — 今天稍早,部分用戶可能因已知的伺服器問題而意外登出 PixAI 帳號,目前此問題已修復。 若您遭遇意外登出,請重新啟動應用程式或瀏覽器,再重新登入即可。若登入後發現帳號不符,可能是因為 Google 登入與電子郵件登入屬於不同帳號,請試著改…

查看詳情

SDXL

Natural Noob XL EPS (Anime/Furry/General)

#獸人
Natural Noob XL EPS (Anime/Furry/General) - AI Model封面圖片
上傳時間
2025年9月6日 上午9:05
使用數
183
評論
非常好  (1)
取樣步數

25

取樣方式

Euler a

CFG Scale

6

反向提示詞

low quality, censored, signature, watermark

許可權
  • 允許圖片生成與分享
  • 允許使用者下載此模型
  • 允許生成圖片用於商業用途

描述

What is this?This is an experimental checkpoint I built by merging a very large number of checkpoints (sorry I didn't think to keep track of each one) using my own iterative merging workflow that involves repeatedly merging (1 step regular, 2 steps DARE) with randomized parameters and then picking the best candidate using a series of manual tests.The goal is a NoobAI checkpoint that is easy to use and works for almost any prompt, with a range of knowledge and styles, and providing a medium level of detail.I put a lot of manual effort into making this checkpoint but occasionally I'll screw something up, so the newest version is usually the most knowledgeable in general, but it may not be the best looking, so I encourage looking at earlier versions.Usage Tips:For the best balance between color and prompt accuracy I like a CFG between 4.0 to 7.0 and 22-32 steps.Use hi-res fix to produce larger images with much more accuracy and detail. I have DARE merged in weights from models designed for higher res images to assist with this :)For some example images I process multiple prompts independently and then concatenate the weights together (helps the model to avoid mixing unrelated subjects). I reconstructed those prompts in the image metadata using "BREAK" to denote where the prompts are concatenated, for compatibility with other workflows that use BREAK syntax.Use a mixture of danbooru & e621 tags, and very simple sentences.

留言

由 Natural Noob XL EPS (Anime/Furry/General) 製作的作品