lightx2v
/

Minimax-h3-Turbo-SLA

video-generation

audio-video-generation

sparse-attention

Model card Files Files and versions

lightx2v commited on about 13 hours ago

Commit

10ade67

·

verified ·

1 Parent(s): 7957fe7

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -29,7 +29,7 @@ The model uses an **85% attention sparsity ratio**. In our tested [LightX2V](htt
 Side-by-side comparison between the 30-step MiniMax-H3 base model and the 4-step MiniMax-H3 Turbo-SLA model:
 <video controls loop muted playsinline width="100%">
-  <source src="https://huggingface.co/lightx2v/Minimax-h3-Turbo-SLA/resolve/main/base30_vs_sla4_side_by_side.mp4" type="video/mp4">
   Your browser does not support the video tag.
 </video>

 Side-by-side comparison between the 30-step MiniMax-H3 base model and the 4-step MiniMax-H3 Turbo-SLA model:
 <video controls loop muted playsinline width="100%">
+  <source src="https://cdn-uploads.huggingface.co/production/uploads/680de13385293771bc57400b/HXV6GbED84PeLteFXqK5l.mp4" type="video/mp4">
   Your browser does not support the video tag.
 </video>