Update README.md
#30
by
Dixonbuttsdrivemenuts
- opened
README.md
CHANGED
|
@@ -122,10 +122,6 @@ Stable Diffusion v2 mirrors and exacerbates biases to such a degree that viewer
|
|
| 122 |
## Training
|
| 123 |
|
| 124 |
**Training Data**
|
| 125 |
-
The model developers used the following dataset for training the model:
|
| 126 |
-
|
| 127 |
-
- LAION-5B and subsets (details below). The training data is further filtered using LAION's NSFW detector, with a "p_unsafe" score of 0.1 (conservative). For more details, please refer to LAION-5B's [NeurIPS 2022](https://openreview.net/forum?id=M3Y74vmsMcY) paper and reviewer discussions on the topic.
|
| 128 |
-
|
| 129 |
**Training Procedure**
|
| 130 |
Stable Diffusion v2 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training,
|
| 131 |
|
|
|
|
| 122 |
## Training
|
| 123 |
|
| 124 |
**Training Data**
|
|
|
|
|
|
|
|
|
|
|
|
|
| 125 |
**Training Procedure**
|
| 126 |
Stable Diffusion v2 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training,
|
| 127 |
|