Update README.md
Browse files
README.md
CHANGED
|
@@ -54,21 +54,19 @@ It achieves the following results on the evaluation set:
|
|
| 54 |
|
| 55 |
_The above example was created with [DALL-E 2](https://labs.openai.com/sc/YbiY2kkuQeODzHNwUHn4D5RN) but will of course work with any text2image model._
|
| 56 |
|
| 57 |
-
## Model description
|
| 58 |
-
|
| 59 |
-
More information needed
|
| 60 |
-
|
| 61 |
## Intended uses & limitations
|
| 62 |
|
| 63 |
-
|
| 64 |
|
| 65 |
## Training and evaluation data
|
| 66 |
|
| 67 |
-
|
| 68 |
|
| 69 |
## Training procedure
|
| 70 |
|
| 71 |
-
|
|
|
|
|
|
|
| 72 |
|
| 73 |
The following hyperparameters were used during training:
|
| 74 |
- learning_rate: 0.0002
|
|
|
|
| 54 |
|
| 55 |
_The above example was created with [DALL-E 2](https://labs.openai.com/sc/YbiY2kkuQeODzHNwUHn4D5RN) but will of course work with any text2image model._
|
| 56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
## Intended uses & limitations
|
| 58 |
|
| 59 |
+
- The model will generate augmentations that are biased towards the training data, i.e. what people already asked for in the SD/midjourney discords, etc. Creating a larger dataset was an attempt at mitigating this through more data from different datasets.
|
| 60 |
|
| 61 |
## Training and evaluation data
|
| 62 |
|
| 63 |
+
See the `pszemraj/text2image-prompts-multi` dataset card for details. The dataset is a compilation of several text-to-image prompt datasets on huggingface :)
|
| 64 |
|
| 65 |
## Training procedure
|
| 66 |
|
| 67 |
+
- this was trained with several training rounds, 8 epochs in total on the train set.
|
| 68 |
+
|
| 69 |
+
### Training hyperparameters (last training round)
|
| 70 |
|
| 71 |
The following hyperparameters were used during training:
|
| 72 |
- learning_rate: 0.0002
|