1

app.py

@@ -78,20 +78,20 @@ def engine(text_input):
         img = gr.Interface.load("spaces/multimodalart/latentdiffusion")(ent[0],'50','256','256','1',10)[0] 
         img_list.append(img)
      
-     #Resizing all images produced to same size
-     resize_img_list = resize(img_list)
+    #Resizing all images produced to same size
+    resize_img_list = resize(img_list)
      
-     #Convert text to speech using facebook's latest model from HF hub   
-     speech = text2speech(text_input)
+    #Convert text to speech using facebook's latest model from HF hub   
+    speech = text2speech(text_input)
      
-     #Calculate the desired frame per second based on given audio length and entities identified
-     fps= entities_num / 19 #length of audio file   #13 / 19
+    #Calculate the desired frame per second based on given audio length and entities identified
+    fps= entities_num / 19 #length of audio file   #13 / 19
      
-     #Convert string of images into a video
-     clip = images_to_video(fps, resize_img_list)
+    #Convert string of images into a video
+    clip = images_to_video(fps, resize_img_list)
      
-     #Merge video and audio created above
-     merged_file = merge_audio_video(speech, clip)
+    #Merge video and audio created above
+    merged_file = merge_audio_video(speech, clip)
     #{'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")], )