PixAI 會員
PixAI
PixAI
Generate
Sign in
主頁
生成
模型
Studio
NEW
比賽
用 Mio.2 創作
AI 工具
NEW
指南

SDXL

Hassaku XL (Illustrious)

AI 工具
  • AI 動漫生成器
  • 動漫手辦生成器
  • 角色設定圖生成器
  • 雜誌封面生成器
  • 玩偶生成器
  • 巨型雕像生成器

探索

  • 熱門 Tags
  • 排名
  • 模型市集
  • 比賽
  • 新聞

關於

  • 指南
  • PixAI 部落格
  • Tsubaki.2
  • 認識 Mio,我們的吉祥物
  • 內容規則

定價與說明

  • 會員計劃
  • 購買點數
  • 聯絡

移動端 APP

  • 下載 PixAI App
  • App Store
  • Google Play
© 2026 PixAI
  • 服務條款
  • 隱私政策
  • 版權政策
  • 第三方內容聲明
  • 特定商業交易法
Hassaku XL (Illustrious) - AI Model cover image
上傳時間
2025年12月10日 上午10:42
使用數
55.2k
評論
非常好  (4)
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

推薦 LoRA

MD cartoon style - AI Model cover image

用戶LoRA

MD cartoon style
50
Ayaka Sajyou (沙条 綾香/アヤカ・サジョウ) - Fate/strange Fake - AI Model cover image

用戶LoRA

Ayaka Sajyou (沙条 綾香/アヤカ・サジョウ) - Fate/strange Fake
41
748cm | Style for Illustrious/NoobAI 0.75 - AI Model cover image

用戶LoRA

748cm | Style for Illustrious/NoobAI 0.75
14.26k
Pony XL - Elaina  イレイナ - majo no tabitabi - AI Model cover image

用戶LoRA

Pony XL - Elaina イレイナ - majo no tabitabi
110

描述

https://civitai.com/models/140272

Model is a WIP! expect 2-3 weekly updates, later beta versions are on my patreon for a short time.

Small compare to other models (done on alpha9) - SFW: miku, blondeDemon, bloodMaid - NSFW: 2nekoGirl, spreadLegs, girlOnTop

My goal is to create a new anime base model, without the need of quality prompts like masterpiece or worst quality. Model focus are good looking anime images and that as easy as possible. My Discord for everything related to anime models. You can also support me on my patreon.

Please use 1girl, 2girls, 3girls.... it is more or less the "masterpiece" prompt of this model. Recommended is also hair and eye colors and a CFG scale of 5-7.

Undertrained concepts appears sometimes to oversaturated, reverts to realism or appear basic and flat. Most training data was simply to put nsfw into the model. Later versions are more stable and don't want to make everything see-through with nipples, skintight and nsfw.

Using the model:

Use mostly danbooru tags. For better promting on it, use this LINK or LINK. But instead of {}, use (), stable-diffusion-webui use ().

Exclude quality prompts like "masterpiece", "best quality", "worst quality", "low quality". My model was not trained with them, I train only with masterpiece and high aesthetic images. I have not the resources to train lower quality images with low quality tags for more diversity. Use 1girl, 2girls, 3girls.... instead, it is more or less the "masterpiece" prompt of this model. Recommended is also hair and eye colors.

Prompt "looking at viewer" is not neccecery, pruned that prompt, default is looking at viewer. Because, if every image used it, no image used it.

Model is trained with images with minimal disruptive features like floating texts, logos and signatures as possible. If such features appearing in a image, use prompt "signature" to use it as negative. I pruned everything down to that single prompt "signature".

Excluded meta data and franchise tags, don't use them (meta data -> something like "highres", franchise tags like "re:zero kara hajimeru isekai seikatsu" are pruned on charaters like "rem_(re:zero)")

For now, artist tags does not work, but will work in the future

by Ikena

留言