Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
license: openrail
|
| 3 |
---
|
| 4 |
-
|
| 5 |
|
| 6 |
How to setup the model
|
| 7 |
======================
|
|
@@ -288,8 +288,6 @@ Comparison to the Original
|
|
| 288 |
Specs and Credits
|
| 289 |
-----------------
|
| 290 |
|
| 291 |
-
|
| 292 |
-
|
| 293 |
The specs are:
|
| 294 |
I trained this DreamBooth model using EveryDream. The model was trained using the art from artist Tokkyu at 57 images, for 3 epochs in a total of 1440 steps. I trained it on a A100 (80gb Vram) with 768x768 native size/variable buckets, batch size 6, at around 68gb Vram per epoch using very high resolution training images non cropped. EveryDream handled the aspect ratios correctly. The images were captioned manually each with a little help from pharmapsychotic's excellent new 2.1 CLIP Interrogator.
|
| 295 |
|
|
|
|
| 1 |
---
|
| 2 |
license: openrail
|
| 3 |
---
|
| 4 |
+
|
| 5 |
|
| 6 |
How to setup the model
|
| 7 |
======================
|
|
|
|
| 288 |
Specs and Credits
|
| 289 |
-----------------
|
| 290 |
|
|
|
|
|
|
|
| 291 |
The specs are:
|
| 292 |
I trained this DreamBooth model using EveryDream. The model was trained using the art from artist Tokkyu at 57 images, for 3 epochs in a total of 1440 steps. I trained it on a A100 (80gb Vram) with 768x768 native size/variable buckets, batch size 6, at around 68gb Vram per epoch using very high resolution training images non cropped. EveryDream handled the aspect ratios correctly. The images were captioned manually each with a little help from pharmapsychotic's excellent new 2.1 CLIP Interrogator.
|
| 293 |
|