Update app.py

app.py

@@ -277,7 +277,7 @@ def run_grounded_sam(input_image, text_prompt, task_type, background_prompt, bac
     #return [(com_img, 'composite with background'), (green_img, 'green screen'), (alpha_rgb, 'alpha matte')]
     return alpha_rgb
 
-def infer(video_in, trim_value, text_prompt, task_type, background_prompt, background_type, box_threshold, text_threshold, iou_threshold, scribble_mode, guidance_mode):
+def infer(video_in, trim_value, text_prompt, background_prompt, background_type, box_threshold, text_threshold, iou_threshold, scribble_mode, guidance_mode):
     print(prompt)
     break_vid = get_frames(video_in)
     
@@ -299,8 +299,8 @@ def infer(video_in, trim_value, text_prompt, task_type, background_prompt, backg
         image_array = np.array(to_numpy_i)
 
         
-        matte_img = run_grounded_sam(image_array, text_prompt, task_type, background_prompt, background_type, box_threshold, text_threshold, iou_threshold, scribble_mode, guidance_mode)
-        #print(pix2pix_img)
+        matte_img = run_grounded_sam(image_array, text_prompt, "text", background_prompt, background_type, box_threshold, text_threshold, iou_threshold, scribble_mode, guidance_mode)
+        #print(pix2pix_img)u
         #image = Image.open(pix2pix_img)
         #rgb_im = image.convert("RGB")
   
@@ -357,7 +357,7 @@ if __name__ == "__main__":
                 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"
+                #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")
@@ -387,7 +387,7 @@ if __name__ == "__main__":
                 video_out = gr.Video()
 
         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)
+                        video_in, trim_in, text_prompt, 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)