Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,12 @@
|
|
| 1 |
---
|
| 2 |
license: openrail
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: openrail
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
A sample from the [Laion 6.5+ ](https://laion.ai/blog/laion-aesthetics/) image + text dataset. You can see
|
| 6 |
+
some samples [here](http://captions.christoph-schuhmann.de/2B-en-6.5.html).
|
| 7 |
+
|
| 8 |
+
The samples are resized + center-cropped to 64x64x3 and the .npz file also contains CLIP embeddings.
|
| 9 |
+
|
| 10 |
+
The data can be used to train a basic text-to-image model.
|
| 11 |
+
|
| 12 |
+
|