Your current browser has compatibility issues. Please switch toChrome for uninterrupted access.

GhostMix

92.8k
439
4.1k
88
AnimeCGI styleAnime StyleGirlStyle BoostMecha
最近更新:24/06/28首次發布:23/05/22
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info
Anime,CGI style,Anime Style,Checkpoint,SD 1.5Image info

Focus on answering questions about image reproduction: First, every one of my previous images was on Huggingface, and Civitai also recreated them, and they can also be recreated next door, including the LIB staff, so there are absolutely no questions that cannot be reproduced. Then, the core problem that cannot be directly reproduced in lib online is the random number generation source, but you can switch to GPU in the advanced settings next to the random seed. SDWEBUI also has this setting. I set the GPU, and the lib setting is the CPU. Different random numbers result in different initial images, which in turn lead to different results. So if you want to reproduce my results, I recommend downloading the model and reproducing

it locally for the time being.

GhostMix

model usage instructions 1. Recommended: Be sure to do HD repairs!

HD restoration: 2x, redraw amplitude: 0.4-0.5 or 1.5 times, redraw amplitude: 0.5-0.65 2. If you want to reproduce, make sure the CLIP value is correct! CLIP1 and CLIP2 are right!

It is recommended to lower the image and put it in the PNG information to check the settings) 3. Most Prompts used before can also generate similar results in the new version 4. Use ng_deepnegative_v1_75t and

easynegative, it is recommended not to use BadHandV4, V5 (it will greatly affect the style)

5. Sampling method is recommended for DPM++ series, steps 20-30, CFG: 3-7 (7 is best, 3 can sometimes be a big surprise

)


全部展開
翻譯成繁體中文

討論8

最熱門
|
最新
發送
avatar
Ticky Tock
Detailed... aww inspiring
2024/05/28 22:11:21
1回覆
avatar
kalu yodah
yes sick
2025/02/11 16:25:42
0回覆
avatar
lirizalifidia_19521
Hi
2025/02/08 03:32:49
0回覆
avatar
Jini669988
请生成相同的照片
2024/11/08 01:14:53
0回覆
avatar
đức chí cao phạm
hi
2024/09/29 07:10:29
0回覆
avatar
鑫鑫
華麗的美
2024/08/18 11:34:46
0回覆
avatar
jajja kakak
hi
2024/07/29 15:23:03
0回覆
avatar
atef ton
She laughs
2024/04/15 15:31:55
0回覆
沒有更多評論
GhostInShell
藝術家
137
2
120.6k
541
收藏
下載
(2.24GB)
已驗證:2023/05/22
safetensors
詳細資訊
類型
Checkpoint
線上生成次數
92.8k
下載次數
439
基礎算法
SD 1.5
推薦參數
採樣器
DPM++ 2M Karras
CFG
7
VAE
高清放大演算法
R-ESRGAN_4x+ Anime6B, 4x-UltraSharp
版權
可以線上生成
不可以合併
商業版權
生成的圖像不能出售或用於商業用途
模型不能轉售或作為合併後的模型出售
*版權範圍由創建者自行設定,用戶必須按照要求和標準使用

圖庫4114

最熱門
|
最新
Pinned
Image info
Image info
Image info
Image info
Image info
Image info
Image info
avatar
Dofas
Image info
Image info
Image info
Image info
avatar
ParisPolyphylla
Image info
Image info
Image info
Image info
avatar
Hades
Image info