Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# KIWI
|
| 2 |
+
|
| 3 |
+
_Shameless plug: If you want a *free open source* fully local booru alternative, I have [created one](https://github.com/demibit/stable-toolkit). It automatically tags your images and let's you easily filter by generation parameters. The [wiki](https://github.com/demibit/stable-toolkit/wiki) has some pictures of how it looks like._
|
| 4 |
+
|
| 5 |
+
## DATASET
|
| 6 |
+
|
| 7 |
+
- **30a**: 30 images of Kiwi, with dimensions of 640x640.
|
| 8 |
+
|
| 9 |
+
## VERSION
|
| 10 |
+
|
| 11 |
+
- **v1**: Trained with clip skip 1 (off) (only applicable for embedding/hypernetwork, as I don't know the status for dreambooth). NAI-analog base model.
|
| 12 |
+
|
| 13 |
+
## DREAMBOOTH
|
| 14 |
+
|
| 15 |
+
[Trained via this GUI](https://github.com/n00mkrad/text2image-gui), but note that it's quite restrictive in training options.
|
| 16 |
+
|
| 17 |
+
- **kiwi-30a-v1**: Trained with "very high quality" preset and "normal" learning rate. [Examples](https://imgur.com/a/sZ3nbrP)
|
| 18 |
+
|
| 19 |
+
## EMBEDDINGS
|
| 20 |
+
|
| 21 |
+
_Currently in training. Will update if it's good._
|
| 22 |
+
|
| 23 |
+
## HYPERNETWORKS
|
| 24 |
+
|
| 25 |
+
_Apparently voldy's hypernetwork training is broken at the moment. Will either rollback, or wait for it to get fixed._
|