Update README.md

README.md

@@ -15,7 +15,23 @@ Images are generated with the keyword, and basic positive/negative prompts as re
 
 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.
 
-Various models are used such as AbyssOrangeMix, Corneos7thHeavenMix, Anything, EveryoneMix.
+Various models are used such as AbyssOrangeMix, Corneos7thHeavenMix, Anything, EveryoneMix, Counterfeit.
+
+## zeta-subject
+
+<img src="https://huggingface.co/soknife/loras/resolve/main/zeta-subject.jpg" width="600"/>
+
+```
+Keyword: vestia zeta
+Keyword: kimono, japanese clothes, vestia zeta
+```
+
+[zeta-subject.safetensors](zeta-subject.safetensors)
+
+<details>
+  <summary>Random sample</summary>
+  <img src="https://huggingface.co/soknife/loras/resolve/main/zeta-subject-sample.jpg" width="600"/>
+</details>
 
 ## suisei-regular-subject