Make new

README.md

@@ -5,20 +5,18 @@ license_name: minimax-h3-community-license-agreement
 license_link: LICENSE
 library_name: minimax-h3
 tags:
-  - text-to-video
-  - image-to-video
-  - image-text-to-video
-  - video-to-video
-  - text-to-audio-video
-  - image-to-audio-video
-  - image-text-to-audio-video
-  - video-to-audio-video
-  - audio-to-audio-video
-  - audio-video-generation
-  - multimodal
-  - synchronized-audio-video
-  - reference-to-audio-video
-  - diffusers
+- text-to-video
+- image-text-to-video
+- video-to-video
+- text-to-audio-video
+- image-to-audio-video
+- image-text-to-audio-video
+- video-to-audio-video
+- audio-to-audio-video
+- audio-video-generation
+- multimodal
+- synchronized-audio-video
+- diffusers
 ---
 
 <div align="center">
@@ -369,7 +367,7 @@ For each case below, we provide reference outputs at both 2K and 768p generated
 #### case\-Ref2VA
 
 - Type: Multimodal reference-to-video (video + audio)
-- Duration: 5 seconds
+- Duration: 20 seconds
 - Aspect ratio: adaptive
 
 <table>
@@ -421,4 +419,4 @@ skills to improve prompt: https://github.com/MiniMax-AI/MiniMax-H3/tree/main/ski
 
 ## Contact Us
 
-Contact us at [model@minimax.io](mailto:model@minimax.io).
+Contact us at [model@minimax.io](mailto:model@minimax.io).