模型/Unspeakable Horrors Negative prompt - Unspeakable Horrors Composition only 4 vectors trained

Unspeakable Horrors Negative prompt - Unspeakable Horrors Composition only 4 vectors trained

|
7/2/2024
|
2:49:19 AM
| Discussion

推薦反向提示詞

negative prompt words

Unspeakable-Horrors-Composition-4v

推薦參數

samplers

DPM++ 2M, Euler a

steps

20 - 60

cfg

7

resolution

640x896, 896x640, 1920x2688, 896x512, 512x960

推薦高解析度參數

denoising strength

0.4

提示

Avoid low multipliers for high vector embeddings, especially on Automatic1111.

Do not use this as a positive embedding.

版本亮點

Trained on about 100 images of terrible color combinations, composition and lighting. Turned out to be quite efficient even with 4 vectors.

It also appears to not like a few things, like rain. In those cases you might need increase their strength.

You still need to use negative prompts like blurry, ugly, motion blur and so on.

創作者贊助

Make sure you check out bad prompt as well.

I've seen horrible things.

But hopefully you don't have to. These embeddings mainly focus on composition, color schemes and anatomy. They are not perfect and should most likely be used along other negative prompt words, but they should do the bulk of the work.

If your model already does good compositions and anatomy, these embeddings might not help. The ones with fewer vectors might be better in this case.

Do note that the way embeddings work with prompt weighting seems somewhat broken, specially on high number of vectors. You can still fine tune, just avoid low multipliers for high vector embeddings, at least on Automatic1111.

These embeddings were also not trained, they were created based on the encoded vectors themselves.

Whatever you do, don't run this as a positive embedding. I'm not responsible for your loss of sanity.

Make sure you check out bad prompt as well.

上一個
epiCPhoto - epiCPhoto
下一個
Boring_e621 Negative Embedding Enhance Images Stylistically AND Topically - fluffyrock v40

模型詳情

模型類型

TextualInversion

基礎模型

SD 1.5

模型版本

Unspeakable Horrors Composition only 4 vectors, trained

模型雜湊值

1e854da9de

創作者

討論

log in以發表評論。