Update app.py

app.py

@@ -1,3 +1,5 @@
+# app.py
+
 import torch
 from diffusers import AutoencoderKLWan, WanImageToVideoPipeline, UniPCMultistepScheduler
 from diffusers.utils import export_to_video
@@ -48,6 +50,8 @@ def _calculate_new_dimensions_wan(pil_image, mod_val, calculation_max_area,
                                  min_slider_h, max_slider_h,
                                  min_slider_w, max_slider_w,
                                  default_h, default_w):
+    if not isinstance(pil_image, Image.Image):
+        return default_h, default_w
     orig_w, orig_h = pil_image.size
     if orig_w <= 0 or orig_h <= 0:
         return default_h, default_w
@@ -65,37 +69,22 @@ def _calculate_new_dimensions_wan(pil_image, mod_val, calculation_max_area,
     
     return new_h, new_w
 
-def handle_image_upload_for_dims_wan(uploaded_pil_image, current_h_val, current_w_val):
-    if uploaded_pil_image is None:
-        return gr.update(value=DEFAULT_H_SLIDER_VALUE), gr.update(value=DEFAULT_W_SLIDER_VALUE)
-    try:
-        new_h, new_w = _calculate_new_dimensions_wan(
-            uploaded_pil_image, MOD_VALUE, NEW_FORMULA_MAX_AREA,
-            SLIDER_MIN_H, SLIDER_MAX_H, SLIDER_MIN_W, SLIDER_MAX_W,
-            DEFAULT_H_SLIDER_VALUE, DEFAULT_W_SLIDER_VALUE
-        )
-        return gr.update(value=new_h), gr.update(value=new_w)
-    except Exception as e:
-        gr.Warning("Error attempting to calculate new dimensions")
-        return gr.update(value=DEFAULT_H_SLIDER_VALUE), gr.update(value=DEFAULT_W_SLIDER_VALUE)
-
-def get_duration(input_image, prompt, height, width, 
+def handle_image_upload_for_dims_wan(uploaded_pil_image):
+    new_h, new_w = _calculate_new_dimensions_wan(
+        uploaded_pil_image, MOD_VALUE, NEW_FORMULA_MAX_AREA,
+        SLIDER_MIN_H, SLIDER_MAX_H, SLIDER_MIN_W, SLIDER_MAX_W,
+        DEFAULT_H_SLIDER_VALUE, DEFAULT_W_SLIDER_VALUE
+    )
+    return gr.update(value=new_h), gr.update(value=new_w)
+
+
+# NOTE: The @spaces.GPU decorator is ignored outside of the Hugging Face platform
+@spaces.GPU
+def generate_video(input_image, prompt, height, width, 
                    negative_prompt, duration_seconds,
                    guidance_scale, steps,
                    seed, randomize_seed, 
-                   progress):
-    if steps > 4 and duration_seconds > 2:
-        return 90
-    elif steps > 4 or duration_seconds > 2:
-        return 75
-    else:
-        return 60
-
-@spaces.GPU(duration=get_duration)
-def generate_video(input_image, prompt, height, width, 
-                   negative_prompt=default_negative_prompt, duration_seconds = 2,
-                   guidance_scale = 1, steps = 4,
-                   seed = 42, randomize_seed = False, 
+                   # *** KEY CHANGE 1: Remove the default value for progress ***
                    progress=gr.Progress(track_tqdm=True)):
     
     if input_image is None:
@@ -115,7 +104,8 @@ def generate_video(input_image, prompt, height, width,
             image=resized_image, prompt=prompt, negative_prompt=negative_prompt,
             height=target_h, width=target_w, num_frames=num_frames,
             guidance_scale=float(guidance_scale), num_inference_steps=int(steps),
-            generator=torch.Generator(device="cuda").manual_seed(current_seed)
+            generator=torch.Generator(device="cuda").manual_seed(current_seed),
+            callback_on_step_end=lambda p, s, l: progress(s / steps) # Use the progress object
         ).frames[0]
 
     with tempfile.NamedTemporaryFile(suffix=".mp4", delete=False) as tmpfile:
@@ -140,7 +130,7 @@ with gr.Blocks() as demo:
                     height_input = gr.Slider(minimum=SLIDER_MIN_H, maximum=SLIDER_MAX_H, step=MOD_VALUE, value=DEFAULT_H_SLIDER_VALUE, label=f"Output Height (multiple of {MOD_VALUE})")
                     width_input = gr.Slider(minimum=SLIDER_MIN_W, maximum=SLIDER_MAX_W, step=MOD_VALUE, value=DEFAULT_W_SLIDER_VALUE, label=f"Output Width (multiple of {MOD_VALUE})")
                 steps_slider = gr.Slider(minimum=1, maximum=30, step=1, value=4, label="Inference Steps") 
-                guidance_scale_input = gr.Slider(minimum=0.0, maximum=20.0, step=0.5, value=1.0, label="Guidance Scale", visible=False)
+                guidance_scale_input = gr.Slider(minimum=0.0, maximum=20.0, step=0.5, value=1.0, label="Guidance Scale") # Set visible=True for debugging if needed
 
             generate_button = gr.Button("Generate Video", variant="primary")
         with gr.Column():
@@ -148,21 +138,16 @@ with gr.Blocks() as demo:
 
     input_image_component.upload(
         fn=handle_image_upload_for_dims_wan,
-        inputs=[input_image_component, height_input, width_input],
-        outputs=[height_input, width_input]
-    )
-    
-    input_image_component.clear( 
-        fn=handle_image_upload_for_dims_wan,
-        inputs=[input_image_component, height_input, width_input],
+        inputs=[input_image_component],
         outputs=[height_input, width_input]
     )
     
+    # Bundle all the UI components that the generate_video function needs
     ui_inputs = [
         input_image_component, prompt_input, height_input, width_input,
         negative_prompt_input, duration_seconds_input,
         guidance_scale_input, steps_slider, seed_input, randomize_seed_checkbox
     ]
-    generate_button.click(fn=generate_video, inputs=ui_inputs, outputs=[video_output, seed_input])
 
-    demo.launch(share=True)
+    # *** KEY CHANGE 2: Add gr.Progress() to the list of inputs for the click event ***
+    generate_button.click(fn=generate_video, inputs=ui_inputs, outputs=[video_output, seed_input])