Audio

app.py

@@ -165,6 +165,7 @@ from dwpose import DwposeDetector
 
 
 input_image_debug_value = [None]
+input_audio_debug_value = [None]
 input_video_debug_value = [None]
 prompt_debug_value = [None]
 total_second_length_debug_value = [None]
@@ -1099,8 +1100,9 @@ class CameraDropdown(gr.HTML):
 
 def generate_video_example(input_image, prompt, camera_lora, resolution, radioanimated_mode, input_video, input_audio, progress=gr.Progress(track_tqdm=True)):
 
-    if input_image_debug_value[0] is not None or end_image_debug_value[0] is not None or prompt_debug_value[0] is not None or total_second_length_debug_value[0] is not None or allocation_time_debug_value[0] is not None or resolution_debug_value[0] is not None or factor_debug_value[0] is not None:
+    if input_image_debug_value[0] is not None or input_audio_debug_value[0] is not None or input_video_debug_value[0] is not None or prompt_debug_value[0] is not None or total_second_length_debug_value[0] is not None or allocation_time_debug_value[0] is not None or resolution_debug_value[0] is not None or factor_debug_value[0] is not None:
         input_image = input_image_debug_value[0]
+        input_audio = input_audio_debug_value[0]
         input_video = input_video_debug_value[0]
         prompt = prompt_debug_value[0]
         duration = total_second_length_debug_value[0]
@@ -2340,6 +2342,7 @@ with gr.Blocks(title="LTX-2 Video Distilled 🎥🔈") as demo:
     )
         prompt_debug=gr.Textbox(label="Prompt Debug")
         input_image_debug=gr.Image(type="filepath", label="Image Debug")
+        input_audio_debug = gr.Audio(label="Audio Debug", type="filepath")
         input_video_debug=gr.Video(label="Video Debug")
         total_second_length_debug=gr.Slider(label="Duration Debug", minimum=1, maximum=120, value=5, step=0.1)
         resolution_debug = gr.Dropdown(
@@ -2356,6 +2359,7 @@ with gr.Blocks(title="LTX-2 Video Distilled 🎥🔈") as demo:
 
     def handle_field_debug_change(
         input_image_debug_data,
+        input_audio_debug_data,
         input_video_debug_data,
         prompt_debug_data,
         total_second_length_debug_data,
@@ -2364,6 +2368,7 @@ with gr.Blocks(title="LTX-2 Video Distilled 🎥🔈") as demo:
         allocation_time_debug_data
     ):
         input_image_debug_value[0] = input_image_debug_data
+        input_audio_debug_value[0] = input_audio_debug_data
         input_video_debug_value[0] = input_video_debug_data
         prompt_debug_value[0] = prompt_debug_data
         total_second_length_debug_value[0] = total_second_length_debug_data
@@ -2372,9 +2377,10 @@ with gr.Blocks(title="LTX-2 Video Distilled 🎥🔈") as demo:
         allocation_time_debug_value[0] = allocation_time_debug_data
         return []
 
-    inputs_debug=[input_image_debug, input_video_debug, prompt_debug, total_second_length_debug, resolution_debug, factor_debug, allocation_time_debug]
+    inputs_debug=[input_image_debug, input_audio_debug, input_video_debug, prompt_debug, total_second_length_debug, resolution_debug, factor_debug, allocation_time_debug]
 
     input_image_debug.upload(fn=handle_field_debug_change, inputs=inputs_debug, outputs=[])
+    input_audio_debug.upload(fn=handle_field_debug_change, inputs=inputs_debug, outputs=[])
     input_video_debug.upload(fn=handle_field_debug_change, inputs=inputs_debug, outputs=[])
     prompt_debug.change(fn=handle_field_debug_change, inputs=inputs_debug, outputs=[])
     total_second_length_debug.change(fn=handle_field_debug_change, inputs=inputs_debug, outputs=[])