Spaces:

HikariDawn
/

This-and-That

Running on Zero

HikariDawn777 commited on Oct 17, 2024

Commit

f4a615b

1 Parent(s): 533f466

Update

Files changed (1) hide show

app.py CHANGED Viewed

@@ -88,7 +88,7 @@ MARKDOWN = \
     This&That is a Robotics scenario (Bridge-dataset-based for this demo) Language-Gesture-Image-conditioned Video Generation Model for Robot Planning.
     This Demo is on the Video Diffusion Model part.
-    Only GestureNet is provided in this Gradio Demo, but you can check the full test code for all pretrained weight available.
     ### Note: The index we put the gesture point by default here is [4, 10] (5th and 11th) for two gesture points or [4] (5th) for one gesture point.
     ### Note: The resolution now only support is 256x384.

     This&That is a Robotics scenario (Bridge-dataset-based for this demo) Language-Gesture-Image-conditioned Video Generation Model for Robot Planning.
     This Demo is on the Video Diffusion Model part.
+    Only VGL mode (image+language+gesture conditioned) is provided in this Demo, but you can check the full test code for all pretrained weight available.
     ### Note: The index we put the gesture point by default here is [4, 10] (5th and 11th) for two gesture points or [4] (5th) for one gesture point.
     ### Note: The resolution now only support is 256x384.