Update README.md
Browse files
README.md
CHANGED
|
@@ -76,7 +76,7 @@ Using the model to generate content that is cruel to individuals is a misuse of
|
|
| 76 |
|
| 77 |
### Bias
|
| 78 |
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
|
| 79 |
-
Stable Diffusion
|
| 80 |
which consists of images that are limited to English descriptions.
|
| 81 |
Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for.
|
| 82 |
This affects the overall output of the model, as white and western cultures are often set as the default. Further, the
|
|
|
|
| 76 |
|
| 77 |
### Bias
|
| 78 |
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
|
| 79 |
+
Stable Diffusion was primarily trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/),
|
| 80 |
which consists of images that are limited to English descriptions.
|
| 81 |
Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for.
|
| 82 |
This affects the overall output of the model, as white and western cultures are often set as the default. Further, the
|