Upload 2806597/3164661/README.md with huggingface_hub

2806597/3164661/README.md

@@ -0,0 +1,71 @@
+---
+license: other
+tags:
+- concept
+- gloryhole
+---
+
+# Krea2 - Gloryhole - v1.0 - 3164661
+
+**Model Type**: LORA
+
+**Base Model**: Krea 2
+
+**Trigger Words**: gh0l3
+
+**Tags**: concept, gloryhole
+
+## Gallery
+
+<table>
+  <tr>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f2f25c48-8e3e-4104-8f67-034fc2539050/original=true/137788465.jpeg" width="200"></td>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/743a0616-7fcd-4369-9e7b-7da136539416/original=true/137786074.jpeg" width="200"></td>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/efaf47ba-539a-4c63-b146-22d5845968a6/original=true/137782811.jpeg" width="200"></td>
+  </tr>
+  <tr>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/7203b44f-8d64-4aa3-9b01-b4275466676a/original=true/137783874.jpeg" width="200"></td>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3891a0d7-df76-42bd-a4ff-33f2b3b25d6c/original=true/137783303.jpeg" width="200"></td>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/41ad9fe1-675c-4603-8d6e-e3cefafab432/original=true/137787932.jpeg" width="200"></td>
+  </tr>
+  <tr>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/88cfd6f1-74ee-4161-abd0-40d224d726e2/original=true/137782425.jpeg" width="200"></td>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/5c4f3778-734e-4f15-921f-185091fee257/original=true/137784452.jpeg" width="200"></td>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e2d52f1e-3f0b-44df-8b56-5b0677bdf8a7/original=true/137785750.jpeg" width="200"></td>
+  </tr>
+  <tr>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/798f4240-2bbe-4ba0-a41e-33195618f048/original=true/137786420.jpeg" width="200"></td>
+  </tr>
+</table>
+
+## Description
+
+Trained on 80 hand-picked images with Rank 32 at 512, 768 and 1024 resolution.
+
+This time I used JoyCaption, which needed relatively little correction, though correcting 80 images still took a while :P
+
+The dataset included:
+
+* Blowjobs, handjobs, vaginal sex, anal sex
+* One woman with two dicks, two women + one penis, and two women with two different dicks
+* Side view, from above, from below, and from behind
+* Close-ups and wider shots
+* Various rooms and lighting conditions
+
+It transfers well to many different ideas and art styles.
+
+Enjoy! If you can remember, it would be awesome to see your creations when you tag the LoRA.
+
+I used the new validation loss graph in AI-Toolkit to find the point where the LoRA starts to overfit. It works pretty well. I trained up to 6500 steps, but after a lot of testing the sweet spot was around 5000 steps**,** even though the graph kept decreasing a bit after that. The validation loss is calculated on images that were not part of the training data (I used three different ones).
+
+![](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2819b015-4bcc-4576-86ec-73171b1adac9/original=true/2819b015-4bcc-4576-86ec-73171b1adac9.jpeg)
+
+---
+
+Author: [AugustusLXIII](https://civitai.com/user/AugustusLXIII)
+
+Model: [CivitAI Model Page](https://civitai.com/models/2806597?modelVersionId=3164661)
+
+Archive: [CivArchive Page](https://civarchive.com/models/2806597?modelVersionId=3164661)
+
+<!-- Version: 20260726_upload -->