er1t0 commited on
Commit
1dcc9e7
1 Parent(s): 9aa9503

update description

Browse files
Files changed (1) hide show
  1. app.py +2 -2
app.py CHANGED
@@ -240,7 +240,7 @@ def process_video(video_path, prompt, target_fps=30, max_dimension=640):
240
  print(traceback.format_exc()) # This will print the full stack trace
241
  return None
242
 
243
- @spaces.GPU(duration=600)
244
  def segment_video(video_file, prompt):
245
  if video_file is None:
246
  return None
@@ -258,7 +258,7 @@ demo = gr.Interface(
258
  description="""
259
  This demo uses [Florence-2](https://huggingface.co/microsoft/Florence-2-large), to enable text-prompted object detection for [SAM2](https://github.com/facebookresearch/segment-anything).
260
 
261
- 1. Upload a short video (< 10 sec , you can fork this space on larger GPU for longer vids)
262
  2. Describe the object to segment (The object should be visible in the first frame).
263
  3. Get your segmented video.
264
  """
 
240
  print(traceback.format_exc()) # This will print the full stack trace
241
  return None
242
 
243
+ @spaces.GPU(duration=300)
244
  def segment_video(video_file, prompt):
245
  if video_file is None:
246
  return None
 
258
  description="""
259
  This demo uses [Florence-2](https://huggingface.co/microsoft/Florence-2-large), to enable text-prompted object detection for [SAM2](https://github.com/facebookresearch/segment-anything).
260
 
261
+ 1. Upload a short video (< 6-7 seconds , you can clone this space on larger GPU for longer vids)
262
  2. Describe the object to segment (The object should be visible in the first frame).
263
  3. Get your segmented video.
264
  """