1

app.py

@@ -151,6 +151,9 @@ def engine(text_input):
     mergedclip = merge_audio_video(entities_num, resize_img_list, text_input)
     print('Back in engine')
     print(' merged clip type :',type(mergedclip))
+    print('Writing the merged video clip to a file')
+    mergedclip.write_videofile('mergedvideo.mp4')
+    print('mergedvideo.mp4 created')
     #{'prompt':text_input,'steps':'50','width':'256','height':'256','images':'1','scale':10}).launch()
     #img_intfc = gr.Interface.load("spaces/multimodalart/latentdiffusion", inputs=[gr.inputs.Textbox(lines=1, label="Input Text"), gr.inputs.Textbox(lines=1, label="Input Text"), gr.inputs.Textbox(lines=1, label="Input Text"), gr.inputs.Textbox(lines=1, label="Input Text"), gr.inputs.Textbox(lines=1, label="Input Text"), gr.inputs.Textbox(lines=1, label="Input Text")],
     #outputs=[gr.outputs.Image(type="pil", label="output image"),gr.outputs.Carousel(label="Individual images",components=["image"]),gr.outputs.Textbox(label="Error")], )
@@ -167,7 +170,7 @@ def engine(text_input):
     #run(prompt, steps, width, height, images, scale)
     
     
-    return mergedclip #img, entities, speech
+    return ('mergedvideo.mp4') #img, entities, speech
     
 #image = gr.outputs.Image(type="pil", label="output image")
 app = gr.Interface(engine,