Update README.md

README.md

@@ -5,7 +5,38 @@ tags:
 - LoRA
 - hunyuan
 ---
-# v2 Arcane Jinx HunyuanVideo LoRA is released
+
+# v3 Arcane Style HunyuanVideo LoRA is released
+<div style="display: flex; gap: 16px;">
+  <video width="33%" height="auto" controls>
+    <source src="https://huggingface.co/Cseti/HunyuanVideo-LoRA-Arcane_Style-v1/resolve/main/test_00223.mp4" type="video/mp4">
+  </video>
+  <video width="33%" height="auto" controls>
+    <source src="https://huggingface.co/Cseti/HunyuanVideo-LoRA-Arcane_Style-v1/resolve/main/test_00228.mp4" type="video/mp4">
+  </video>
+  <video width="33%" height="auto" controls>
+    <source src="https://huggingface.co/Cseti/HunyuanVideo-LoRA-Arcane_Style-v1/resolve/main/test_00238.mp4" type="video/mp4">
+  </video>
+</div>
+
+## ID Token / Trigger word(s):
+Use this in your prompt helps providing the style.
+
+- csetiarcane animation style
+
+## Trainig details:
+It was trained on images and videos
+- LR: 2e-5
+- Optimizer: adamw
+- epochs: 22
+- steps: 7326
+- dataset: 135 videos and 135 images
+- repeats: 5
+- rank: 128
+- batch size: 1
+- gradient accumulation steps: 4
+
+# v2 Arcane Style HunyuanVideo LoRA is released
 
 ## Advantages:
 - Better image quality than the v1
@@ -27,7 +58,7 @@ Use this in your prompt helps providing the style.
 - batch size: 1
 - gradient accumulation steps: 4
 
-# Arcane Jinx HunyuanVideo LoRA v1
+# Arcane Style HunyuanVideo LoRA v1
 
 <div style="display: flex; gap: 16px;">
   <video width="33%" height="auto" controls>