Update README.md
Browse files
README.md
CHANGED
|
@@ -19,16 +19,15 @@ This model was not trained with A.I. generated images or merged with any other m
|
|
| 19 |
The largest portion of the dataset consists of photographs of women, men, gorgeous landscapes, and luxurious home/cabin/hotel interiors, some abandoned buildings and cityscapes, followed by a few unique art styles that can most easily be discovered by prompting with the commonly used words below.
|
| 20 |
|
| 21 |
Some tips for realistic images:
|
| 22 |
-
|
| 23 |
-
part of the dataset contains "realistic porcelain dolls" and it will likely reference those dolls to a degree when prompted. I tend to avoid that word anyways because "realistic" is usually used to describe high quality paintings, cgi, or other classically non realistic artforms and when I want realism I'm trying to reference photographs but do whatever works for you, there's plenty of latent space to explore and I'm no expert. It shouldn't be an issue but If your faces look a bit smoother than you like try throwing the word "doll" in the negative prompt.
|
| 24 |
This model is great at both high detailed realism and stylized images so keep these two words in mind when generating.
|
| 25 |
|
| 26 |
-
A few
|
| 27 |
-
Papercut
|
| 28 |
-
Liquid Splash
|
| 29 |
-
Realistic Porcelain Doll
|
| 30 |
-
Interior
|
| 31 |
-
Landscape
|
| 32 |
...and a few others for you to discover.
|
| 33 |
|
| 34 |
If your so inclined to leave a tip I'm happy to accept monero at this address:
|
|
|
|
| 19 |
The largest portion of the dataset consists of photographs of women, men, gorgeous landscapes, and luxurious home/cabin/hotel interiors, some abandoned buildings and cityscapes, followed by a few unique art styles that can most easily be discovered by prompting with the commonly used words below.
|
| 20 |
|
| 21 |
Some tips for realistic images:
|
| 22 |
+
part of the dataset contains "realistic porcelain dolls" It shouldn't be an issue but If your faces look a bit smoother than you like try throwing the word "doll" in the negative prompt.
|
|
|
|
| 23 |
This model is great at both high detailed realism and stylized images so keep these two words in mind when generating.
|
| 24 |
|
| 25 |
+
A few commonly used words found in the training dataset include:
|
| 26 |
+
**Papercut**
|
| 27 |
+
**Liquid Splash**
|
| 28 |
+
**Realistic Porcelain Doll**
|
| 29 |
+
**Interior**
|
| 30 |
+
**Landscape**
|
| 31 |
...and a few others for you to discover.
|
| 32 |
|
| 33 |
If your so inclined to leave a tip I'm happy to accept monero at this address:
|