Update README.md
Browse files
README.md
CHANGED
@@ -5,8 +5,29 @@ tags:
|
|
5 |
- lora
|
6 |
---
|
7 |
|
8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
|
10 |
LORA trained on open source fantasy landscape art from the shut down game [Duelyst](https://en.wikipedia.org/wiki/Duelyst), whose assets have been uploaded to GitHub under the CC0 license.
|
11 |
|
12 |
-
Dataset obtained from [The Public Conscious](http://library.lowframerate.games/), a collection of public domain images.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
- lora
|
6 |
---
|
7 |
|
8 |
+
## Duelyst Codex LORA
|
9 |
+
|
10 |
+
(Model Card will be updated later with proper example images and prompt settings, WIP)
|
11 |
+
|
12 |
+
<img src="https://huggingface.co/cadaeic/duelyst-codex-lora/resolve/main/im_20230222110424_000_988913356.png"/>
|
13 |
+
|
14 |
+
**Prompt:** painting of a fantasy landscape of a castle
|
15 |
+
|
16 |
+
---
|
17 |
|
18 |
LORA trained on open source fantasy landscape art from the shut down game [Duelyst](https://en.wikipedia.org/wiki/Duelyst), whose assets have been uploaded to GitHub under the CC0 license.
|
19 |
|
20 |
+
Dataset obtained from [The Public Conscious](http://library.lowframerate.games/), a collection of public domain images.
|
21 |
+
|
22 |
+
### Notes
|
23 |
+
|
24 |
+
- Trained over Stable Diffusion 1.5 and will work with SD 1.x models
|
25 |
+
- Overtrained on fantasy landscapes
|
26 |
+
- My very first Lora, and pretty much a test Lora!
|
27 |
+
- Trained with [this Colab notebook](https://colab.research.google.com/github/Linaqruf/kohya-trainer/blob/main/kohya-LoRA-finetuner.ipynb) using default settings with a free Google colab account for 40 minutes
|
28 |
+
|
29 |
+
---
|
30 |
+
|
31 |
+
<img src="https://huggingface.co/cadaeic/duelyst-codex-lora/resolve/main/im_20230222110707_001_141397401.png"/>
|
32 |
+
|
33 |
+
**Prompt:** fantasy painting of a fat grey british shorthair cat
|