Update app.py

app.py

@@ -274,7 +274,8 @@ def run_grounded_sam(input_image, text_prompt, task_type, background_prompt, bac
     ### com img with green screen
     green_img = alpha_pred[..., None] * image_ori + (1 - alpha_pred[..., None]) * np.array([PALETTE_back], dtype='uint8')
     green_img = np.uint8(green_img)
-    return [(com_img, 'composite with background'), (green_img, 'green screen'), (alpha_rgb, 'alpha matte')]
+    #return [(com_img, 'composite with background'), (green_img, 'green screen'), (alpha_rgb, 'alpha matte')]
+    return alpha_rgb
 
 def infer(prompt,video_in, trim_value):
     print(prompt)
@@ -354,11 +355,13 @@ if __name__ == "__main__":
         with gr.Row():
             with gr.Column():
                 video_in = gr.Video(source='upload', type="filepath")
+                trim_in = gr.Slider(label="Cut video at (s)", minimun=1, maximum=5, step=1, value=1
                 #task_type = gr.Dropdown(["scribble_point", "scribble_box", "text"], value="text", label="Prompt type")
                 task_type = "text"
                 text_prompt = gr.Textbox(label="Text prompt", placeholder="the girl in the middle")
                 background_type = gr.Dropdown(["generated_by_text", "real_world_sample"], value="generated_by_text", label="Background type")
                 background_prompt = gr.Textbox(label="Background prompt", placeholder="downtown area in New York")
+                
                 run_button = gr.Button(label="Run")
                 with gr.Accordion("Advanced options", open=False):
                     box_threshold = gr.Slider(
@@ -378,12 +381,13 @@ if __name__ == "__main__":
                     )
 
             with gr.Column():
-                gallery = gr.Gallery(
-                    label="Generated images", show_label=True, elem_id="gallery"
-                ).style(preview=True, grid=3, object_fit="scale-down")
+                #gallery = gr.Gallery(
+                #    label="Generated images", show_label=True, elem_id="gallery"
+                #).style(preview=True, grid=3, object_fit="scale-down")
+                video_out = gr.Video()
 
-        run_button.click(fn=run_grounded_sam, inputs=[
-                        input_image, text_prompt, task_type, background_prompt, background_type, box_threshold, text_threshold, iou_threshold, scribble_mode, guidance_mode], outputs=gallery)
+        run_button.click(fn=infer, inputs=[
+                        video_in, trim_in, text_prompt, task_type, background_prompt, background_type, box_threshold, text_threshold, iou_threshold, scribble_mode, guidance_mode], outputs=video_out)
 
     block.launch(debug=args.debug, share=args.share, show_error=True)
     #block.queue(concurrency_count=100)