Update app.py

app.py

@@ -1,9 +1,7 @@
-#!/usr/bin/env python
-
+##!/usr/bin/env python
 import os
 import pathlib
 import tempfile
-
 import gradio as gr
 import torch
 from huggingface_hub import snapshot_download
@@ -11,24 +9,18 @@ from modelscope.outputs import OutputKeys
 from modelscope.pipelines import pipeline
 
 DESCRIPTION = "# ModelScope-Image2Video"
-if not torch.cuda.is_available():
-    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
-
-if torch.cuda.is_available():
-    model_cache_dir = os.getenv("MODEL_CACHE_DIR", "./models")
-    model_dir = pathlib.Path(model_cache_dir) / "MS-Image2Video"
-    snapshot_download(repo_id="damo-vilab/MS-Image2Video", repo_type="model", local_dir=model_dir)
-    pipe = pipeline(task="image-to-video", model=model_dir.as_posix(), model_revision="v1.1.0", device="cuda:0")
-else:
-    pipe = None
+DESCRIPTION += "\n<p>Running on CPU. Performance may be slower compared to GPU.</p>"
 
+model_cache_dir = os.getenv("MODEL_CACHE_DIR", "./models")
+model_dir = pathlib.Path(model_cache_dir) / "MS-Image2Video"
+snapshot_download(repo_id="damo-vilab/MS-Image2Video", repo_type="model", local_dir=model_dir)
+pipe = pipeline(task="image-to-video", model=model_dir.as_posix(), model_revision="v1.1.0", device="cpu")
 
 def image_to_video(image_path: str) -> str:
     output_file = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False)
     pipe(image_path, output_video=output_file.name)[OutputKeys.OUTPUT_VIDEO]
     return output_file.name
 
-
 with gr.Blocks(css="style.css") as demo:
     gr.Markdown(DESCRIPTION)
     gr.DuplicateButton(
@@ -40,7 +32,6 @@ with gr.Blocks(css="style.css") as demo:
         input_image = gr.Image(label="Input image", type="filepath")
         run_button = gr.Button()
         output_video = gr.Video(label="Output video")
-
     run_button.click(
         fn=image_to_video,
         inputs=input_image,
@@ -49,4 +40,4 @@ with gr.Blocks(css="style.css") as demo:
     )
 
 if __name__ == "__main__":
-    demo.queue(max_size=10).launch()
+    demo.queue(max_size=10).launch()