详情
相关作品
CryMiji\v4.0🥇
Wendetta/v3.0🥈
🔝HXMiji/v2.5 [Final]
🔝iL2.3
Special|Zeno🎂
UniJi/QBug
ZeRO/QBug
PSYMiji/v2/V-Pred
PSYMiji/V-Pred
iL2.1
MadLy_IL2.8D [Unstable]
Miji5
Noob/v0.7
Ponyji
Y
REV
iL2.0
☂️𝑵𝒆𝒐𝑴𝒊𝑱𝒊☂️
原创

☂️𝑵𝒆𝒐𝑴𝒊𝑱𝒊☂️

561.0K
2.1K
0
#Realism
#动漫
#Miji
#男性
#女性
#风格
#Illustrious
...查看更多

Read descriptions of models and their versions; all changes are noted there.


Change DateProductVersionStatus / ActionNote
Apr 01, 2026EvilJuicev2.4🗑️ DeletedVersion
Apr 14, 2026Wendettav3.0🚀 ReleasedNew release
Apr 21, 2026CryMijiv4.0🚀 ReleasedNew release


🎬 MY SETTINGS 🎬

📸 CLIP SKIP: 2
🎲
CFG Scale: 4.5 | 5 | 5.5 | 6 (Optimal)
🧼
Samplers / Schedulers: Euler A, DPM++ 2M SDE, SGM Uniform, BETA, Karras
👣
Steps: 20 — 40
♨️
Hi-Res Fix: 4x-UltraSharp or Foolhardy Remacri (Don't use it now)
🎭
Adetailer: Use for Face and Eyes if you have problems with them

PROMPT PARAMETERS

✔️ Quality (Illustrious): masterpiece, best quality, very aesthetic

Negative Prompt: watermark, signature, copyright name, artist name, logo, text, english text, artist logo, twitter logo, twitter username, character name, patreon name, patreon logo, worst quality, low quality, normal quality, lowres, bad , bad hands, extra digits, missing fingers, error, blurry, text, child, childish, , ,

💡 ADDITIONAL NOTES 💡

⚠️ Scheduler: You can use your own scheduler, but it is not recommended.
⚙️
CFG: You can adjust Classifier-Free Guidance to a greater or lesser extent, but the settings listed above are those I used.
💎 VAE: Baked into Model.

查看译文

评分与评论

4.6 /5

尚未收到足够的评分或评论

更多
no-data
暂无数据
avatar
avatar_frame
Whyxeo
623
17.9K
与模型对话
公告
2025-05-15
发布模型
2026-04-23
更新模型信息
模型详情
类型
Checkpoint
发布时间
2026-04-21
基础模型
Illustrious
模型参数
sampler:Euler a
cfg_scale:5.5
steps:35
vae:None
查看更多
训练参数
Epochs:1
Steps:0
版本介绍

🧬 Full Description: CryMiji| v/4.0

Based on: Special [CryWhyx_beta2]


What's new in this version:

🔥 Crispier details: Greatly improved attention to detail, attention to style, better prompt understanding, stability and quality.

🎲 Style details: improvements in drawing style, medium niji\miji style remixed semi-anime.

🦊 Furry support.

✨ Better effects: Fine-tuned lighting and visual effects for a cleaner look.

🎨 LoRA-friendly: Compatible with other style LoRAs

Please note; - read the recommended settings and resolution for the model and you will get the best image quality.


💎 A Personal Note;

Stable version, contains a medium mixed miji style, the model remains flexible, works with Danbooru authors and their tags, can work with other style LoRAs.

Please give your like and heart for my works! For you it's cost nothing, for me it's motivation to move on <3

许可范围
创作许可范围
在线生图
进行融合
允许下载
商业许可范围
生成图片可出售或用于商业目的
允许模型转售或融合后出售
QR Code
下载SeaArt App
在移动端继续你的AI创作之旅