Upload 2895273/3273104/README.md with huggingface_hub

2895273/3273104/README.md

@@ -0,0 +1,41 @@
+---
+license: other
+tags:
+- character
+---
+
+# Minimax h3 Astro NSFW - v1.0 - 3273104
+
+**Model Type**: LORA
+
+**Base Model**: MiniMax H3
+
+**Trigger Words**: None
+
+**Tags**: character
+
+## Gallery
+
+<table>
+  <tr>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e61d041e-8778-452e-9732-b6255402d1be/original=true/141041195.mp4" width="200" controls muted autoplay loop></video></td>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a3d35667-d7a6-4d08-afc8-089312c6e81e/original=true/141043283.mp4" width="200" controls muted autoplay loop></video></td>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0ffcf6e6-cf99-4584-a53c-557d63bef1ec/original=true/141043507.mp4" width="200" controls muted autoplay loop></video></td>
+  </tr>
+</table>
+
+## Description
+
+This lora has been trained with over 5000 clips, improving human movement and anatomy. It can also interact with non-human objects. No trigger word is required.
+
+Training process: Videos were scraped from the internet and trimmed to between 5 and 15 seconds. Tagging was done by hiring freelancers; 30% of the dataset was tagged and other 70% tagged by llm, and GPUs were rented at Runpod. Future versions will have a higher percentage of the dataset tagged and more training time.
+
+---
+
+Author: [astronopor](https://civitai.com/user/astronopor)
+
+Model: [CivitAI Model Page](https://civitai.com/models/2895273?modelVersionId=3273104)
+
+Archive: [CivArchive Page](https://civarchive.com/models/2895273?modelVersionId=3273104)
+
+<!-- Version: 20260828_upload -->