feat: refactor

app.py

@@ -15,10 +15,24 @@ import imageio
 from media_pipe.draw_util import FaceMeshVisualizer
 
 from download_models import download 
+import torch
 
 # Download models and check for exists
 download()
 
+# Check GPU availability
+print("="*50)
+print("🔍 GPU Status Check:")
+print(f"   PyTorch version: {torch.__version__}")
+print(f"   CUDA available: {torch.cuda.is_available()}")
+if torch.cuda.is_available():
+    print(f"   CUDA version: {torch.version.cuda}")
+    print(f"   GPU device: {torch.cuda.get_device_name(0)}")
+    print(f"   GPU count: {torch.cuda.device_count()}")
+else:
+    print("   ⚠️  No CUDA GPU detected - will use CPU")
+print("="*50)
+
 PROCESSED_VIDEO_DIR = './processed_videos'
 TEMP_DIR = './temp'
 INFER_CONFIG_PATH = './configs/infer.yaml'
@@ -255,46 +269,47 @@ def generate_video(input_img, should_crop_face, expand_x, expand_y, offset_x, of
     return status, oo_video_path, all_video_path, frames_archive
 
 with gr.Blocks() as demo:
-    gr.Markdown("# FollowYourEmoji Webui")
-    
-    gr.Markdown("""
-    ## 📖 How to Use This Demo
+    gr.Markdown("<h1 style='text-align: center;'>FollowYourEmoji</h1>")
     
-    Follow these simple steps to create your animated emoji video:
+    # GPU Status Display
+    gpu_available = torch.cuda.is_available()
+    gpu_info = ""
+    if gpu_available:
+        gpu_name = torch.cuda.get_device_name(0)
+        gpu_info = f"🚀 **GPU Enabled**: {gpu_name}"
+    else:
+        gpu_info = "⚠️ **Running on CPU** (Generation will be slower)"
     
-    1. **📸 Upload Reference Image**: Upload a portrait photo in the left panel
-    2. **✂️ Crop Face (Optional)**: Enable face cropping to automatically fit the image to match the video motion
-    3. **🎬 Upload Reference Video**: Upload a video or select a preprocessed .npy file in the middle panel
-    4. **👁️ Preview Animation**: Click "Show Animation preview" to see how the motion will look
-    5. **⚙️ Adjust Settings**: Fine-tune generation parameters at the bottom (steps, CFG scale, FPS, etc.)
-    6. **🎨 Generate Video**: Click "Generate Video" to create your animated result
+    gr.Markdown(f"<div style='text-align: center; padding: 10px; background-color: #f0f0f0; border-radius: 5px;'>{gpu_info}</div>")
     
-    💡 **Tips**: 
-    - Use face cropping if your portrait is too far away or doesn't align well
-    - Preview the animation before generating to ensure the motion looks good
-    - Try the examples below to get started quickly!
-    """)
+    with gr.Box():
+        gr.Markdown("""
+        <div style='text-align: center;'>
+        
+        ## 📖 How to Use This Demo
+        
+        Follow these simple steps to create your animated emoji video:
+        
+        **1. 📸 Upload Reference Image** → Upload a portrait photo in the left panel  
+        **2. 🎬 Upload Reference Video** → Upload a video or select a preprocessed .npy file in the middle panel  
+        **3. ✂️ Crop Face (Optional)** → Enable face cropping to automatically fit the image to match the video motion  
+        **4. 👁️ Preview Animation** → Click "Show Animation preview" to see how the motion will look  
+        **5. ⚙️ Adjust Settings** → Fine-tune generation parameters at the bottom (steps, CFG scale, FPS, etc.)  
+        **6. 🎨 Generate Video** → Click "Generate Video" to create your animated result
+        
+        💡 **Tips**: Use face cropping if your portrait is too far away • Preview the animation before generating • Try the examples below!
+        
+        </div>
+        """)
     
     # Main Layout: 3 columns - Image, Video, Results
     with gr.Row():
-        # Left Column: Image Upload and Crop Face
+        # Left Column: Image Upload
         with gr.Column(scale=1):
             gr.Markdown("### 📸 Reference Image")
             input_img = gr.Image(label="Upload reference image", type="filepath", height=400)
-            
-            crop_face_checkbox = gr.Checkbox(label="Crop face according to video",info="If your picture is too far away or the face doesn't fit you can use cropping", value=False)
-            with gr.Accordion("Face Cropping Settings", open=False):
-                expand_x = gr.Slider(label="Expand X", minimum=0.5, maximum=5.0, value=1.2, step=0.01)
-                expand_y = gr.Slider(label="Expand Y", minimum=0.5, maximum=5.0, value=1.2, step=0.01)
-                offset_x = gr.Slider(label="Offset X", minimum=-1, maximum=1, value=0.0, step=0.01)
-                offset_y = gr.Slider(label="Offset Y", minimum=-1, maximum=1, value=0.0, step=0.01)
-                
-                preview_crop_btn = gr.Button(value="Preview Crop", variant="secondary")
-                with gr.Row():
-                    crop_preview = gr.Image(label="Crop Preview", height=200)
-                    crop_preview_motion = gr.Image(label="Motion Preview", height=200)
         
-        # Middle Column: Video Input and Animation Preview
+        # Middle Column: Video Input, Crop Face, and Animation Preview
         with gr.Column(scale=1):
             gr.Markdown("### 🎬 Reference Video")
             input_video_type = gr.Radio(label="Input type", choices=["video","npy"], value="video")
@@ -308,6 +323,19 @@ with gr.Blocks() as demo:
                 input_npy_refresh = gr.Button(value="Refresh NPY List")
                 input_npy = gr.File(file_types=[".npy"], label="Upload .npy file")
             
+            gr.Markdown("---")
+            crop_face_checkbox = gr.Checkbox(label="✂️ Crop face according to video",info="Enable this after uploading both image and video", value=False)
+            with gr.Accordion("Face Cropping Settings", open=False):
+                expand_x = gr.Slider(label="Expand X", minimum=0.5, maximum=5.0, value=1.2, step=0.01)
+                expand_y = gr.Slider(label="Expand Y", minimum=0.5, maximum=5.0, value=1.2, step=0.01)
+                offset_x = gr.Slider(label="Offset X", minimum=-1, maximum=1, value=0.0, step=0.01)
+                offset_y = gr.Slider(label="Offset Y", minimum=-1, maximum=1, value=0.0, step=0.01)
+                
+                preview_crop_btn = gr.Button(value="Preview Crop", variant="secondary")
+                with gr.Row():
+                    crop_preview = gr.Image(label="Crop Preview", height=200)
+                    crop_preview_motion = gr.Image(label="Motion Preview", height=200)
+            
             with gr.Accordion("Animation Preview", open=False):
                 show_gif_btn = gr.Button(value="Show Animation Preview", variant="secondary")
                 with gr.Row():
@@ -366,13 +394,19 @@ with gr.Blocks() as demo:
     input_video.change(
         fn=process_input_video,
         inputs=[input_video, input_video_save],
-        outputs=[result_status, input_npy, input_video_frames, output_fps_info]
+        outputs=[result_status, input_npy, input_video_frames, output_fps_info],
+        show_progress="full"
     )
 
     input_npy_select.change(fn=update_frame_count, inputs=[input_npy_select], outputs=[input_video_frames])
     input_npy.change(fn=update_frame_count, inputs=[input_npy], outputs=[input_video_frames])
 
-    show_gif_btn.click(fn=show_gif_for_npy, inputs=[input_npy_select, input_video], outputs=[gif_output, gif_output_align, result_status])
+    show_gif_btn.click(
+        fn=show_gif_for_npy, 
+        inputs=[input_npy_select, input_video], 
+        outputs=[gif_output, gif_output_align, result_status],
+        show_progress="full"
+    )
 
     input_video.change(
         fn=update_gif_on_video_change,
@@ -385,7 +419,8 @@ with gr.Blocks() as demo:
     preview_crop_btn.click(
         fn=preview_crop,
         inputs=[input_img, input_npy_select, input_video, expand_x, expand_y, offset_x, offset_y],
-        outputs=[crop_preview,crop_preview_motion, result_status]
+        outputs=[crop_preview,crop_preview_motion, result_status],
+        show_progress="full"
     )
 
     result_btn.click(
@@ -393,7 +428,8 @@ with gr.Blocks() as demo:
         inputs=[input_img, crop_face_checkbox, expand_x, expand_y, offset_x, offset_y, input_video_type, input_video, input_npy_select, input_npy, input_video_frames,
             settings_steps, settings_cfg_scale, settings_seed, resolution_w, resolution_h,
             model_step, custom_output_path, use_custom_fps, output_fps, callback_steps, context_frames, context_stride, context_overlap, context_batch_size, anomaly_action,intropolate_factor],
-        outputs=[result_status, result_video, result_video_2, frames_output]
+        outputs=[result_status, result_video, result_video_2, frames_output],
+        show_progress="full"
     )
     
     # Examples Section