Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,31 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: creativeml-openrail-m
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
license: creativeml-openrail-m
|
| 5 |
+
thumbnail:
|
| 6 |
+
tags:
|
| 7 |
+
- stable-diffusion
|
| 8 |
+
- text-to-image
|
| 9 |
+
- image-to-image
|
| 10 |
---
|
| 11 |
+
|
| 12 |
+
# Some LoRAs
|
| 13 |
+
|
| 14 |
+
Images are generated with the keyword, and basic positive/negative prompts as recommended by the model's creator. The medium strength LoRA is used and weight is set to 1, stronger and weaker LoRA are also provided.
|
| 15 |
+
|
| 16 |
+
Hero images are cherry picked with a few additional prompts. Sample images are randomly generated without cherry picking. This is to show the inheritant biases of the LoRA.
|
| 17 |
+
|
| 18 |
+
Various models are used such as AbyssOrangeMix, Corneos7thHeavenMix, Anything, EveryoneMix.
|
| 19 |
+
|
| 20 |
+
## irys-regular-subject
|
| 21 |
+
|
| 22 |
+
<img src="https://huggingface.co/soknife/loras/resolve/main/irys-regular-subject.jpg" width="600"/>
|
| 23 |
+
|
| 24 |
+
Keyword: irys \(hololive\)
|
| 25 |
+
|
| 26 |
+
[irys-regular-subject.pt](irys-regular-subject.pt)
|
| 27 |
+
|
| 28 |
+
<details>
|
| 29 |
+
<summary>Random sample</summary>
|
| 30 |
+
<img src="https://huggingface.co/soknife/loras/resolve/main/irys-regular-subject-sample.jpg" width="600"/>
|
| 31 |
+
</details>
|