ZeroCool94
commited on
Commit
•
eaf367a
1
Parent(s):
3430701
Update README.md
Browse files
README.md
CHANGED
@@ -2,8 +2,10 @@
|
|
2 |
license: openrail++
|
3 |
language:
|
4 |
- en
|
|
|
|
|
5 |
widget:
|
6 |
-
|
7 |
tags:
|
8 |
- stable-diffusion
|
9 |
- sygil-diffusion
|
@@ -18,8 +20,9 @@ pinned: true
|
|
18 |
|
19 |
# About the model
|
20 |
-----------------
|
21 |
-
This model is a fine-tune of Stable Diffusion v1.5, trained on the [Imaginary Network Expanded Dataset](https://github.com/Sygil-Dev/INE-dataset), with the big advantage of allowing the use of multiple namespaces (labeled tags) to control various parts of the final generation.
|
22 |
-
While current models usually are prone to “context errors” and need substantial negative prompting to set them on the right track, the use of namespaces in this model (eg. “species:seal” or “studio:dc”) stop the model from misinterpreting a seal as the singer Seal, or DC
|
|
|
23 |
|
24 |
As the model is fine-tuned on a wide variety of content, it’s able to generate many types of images and compositions, and easily outperforms the original model when it comes to portraits, architecture, reflections, fantasy, concept art, and landscapes without being hyper-specialized like other community fine-tunes that are currently available.
|
25 |
|
|
|
2 |
license: openrail++
|
3 |
language:
|
4 |
- en
|
5 |
+
- zh
|
6 |
+
- ja
|
7 |
widget:
|
8 |
+
- text: a beautiful illustration of a fantasy forest
|
9 |
tags:
|
10 |
- stable-diffusion
|
11 |
- sygil-diffusion
|
|
|
20 |
|
21 |
# About the model
|
22 |
-----------------
|
23 |
+
This model is a fine-tune of Stable Diffusion v1.5, trained on the [Imaginary Network Expanded Dataset](https://github.com/Sygil-Dev/INE-dataset), with the big advantage of allowing the use of multiple namespaces (labeled tags) to control various parts of the final generation.
|
24 |
+
While current models usually are prone to “context errors” and need substantial negative prompting to set them on the right track, the use of namespaces in this model (eg. “species:seal” or “studio:dc”) stop the model from misinterpreting a seal as the singer Seal, or DC Comics as Washington DC.
|
25 |
+
This model is also able to understand other languages besides English, currently it can partially understand prompts in Chinese, Japanese and Spanish. More training is already being done in order to have the model completely understand those languages and have it work just like how it works with English prompts.
|
26 |
|
27 |
As the model is fine-tuned on a wide variety of content, it’s able to generate many types of images and compositions, and easily outperforms the original model when it comes to portraits, architecture, reflections, fantasy, concept art, and landscapes without being hyper-specialized like other community fine-tunes that are currently available.
|
28 |
|