Commit
•
12b0372
1
Parent(s):
cf8a6e8
Add info about best embeddings
Browse files
README.md
CHANGED
|
@@ -8,6 +8,9 @@ tags:
|
|
| 8 |
The embeddings in this repository were trained for the 768px [Stable Diffusion v2.0](https://huggingface.co/stabilityai/stable-diffusion-2) model. The embeddings should work on any model that uses SD v2.0 as a base.
|
| 9 |
|
| 10 |
|
|
|
|
|
|
|
|
|
|
| 11 |
**Knollingcase v1**
|
| 12 |
|
| 13 |
The v1 embeddings were trained for 4000 iterations with a batch size of 2, a text dropout of 10%, & 16 vectors using Automatic1111's WebUI. A total of 69 training images with high quality captions were used.
|
|
|
|
| 8 |
The embeddings in this repository were trained for the 768px [Stable Diffusion v2.0](https://huggingface.co/stabilityai/stable-diffusion-2) model. The embeddings should work on any model that uses SD v2.0 as a base.
|
| 9 |
|
| 10 |
|
| 11 |
+
Currently the kc32-v4-5000.pt & kc16-v4-5000.pt embeddings seem to perform the best.
|
| 12 |
+
|
| 13 |
+
|
| 14 |
**Knollingcase v1**
|
| 15 |
|
| 16 |
The v1 embeddings were trained for 4000 iterations with a batch size of 2, a text dropout of 10%, & 16 vectors using Automatic1111's WebUI. A total of 69 training images with high quality captions were used.
|