Update app.py

app.py

@@ -1,15 +1,12 @@
 import gradio as gr
-#import gradio.helpers
 import torch
 import os
 from glob import glob
 from pathlib import Path
 from typing import Optional
-
 from diffusers import StableVideoDiffusionPipeline
 from diffusers.utils import load_image, export_to_video
 from PIL import Image
-
 import uuid
 import random
 from huggingface_hub import hf_hub_download
@@ -18,7 +15,7 @@ import spaces
 pipe = StableVideoDiffusionPipeline.from_pretrained(
     "vdo/stable-video-diffusion-img2vid-xt-1-1", torch_dtype=torch.float16, variant="fp16"
 )
-pipe.to("cuda")
+pipe.to("cpu")
 
 max_64_bit_int = 2**63 - 1
 
@@ -31,7 +28,7 @@ def sample(
     fps_id: int = 6,
     version: str = "svd_xt",
     cond_aug: float = 0.02,
-    decoding_t: int = 3,  # Number of frames decoded at a time! This eats most VRAM. Reduce if necessary.
+    decoding_t: int = 3,  
     device: str = "cuda",
     output_folder: str = "outputs",
 ):
@@ -53,40 +50,30 @@ def sample(
     return video_path, frames, seed
 
 def resize_image(image, output_size=(1024, 576)):
-    # Calculate aspect ratios
-    target_aspect = output_size[0] / output_size[1]  # Aspect ratio of the desired size
-    image_aspect = image.width / image.height  # Aspect ratio of the original image
+    target_aspect = output_size[0] / output_size[1]  
+    image_aspect = image.width / image.height  
 
-    # Resize then crop if the original image is larger
     if image_aspect > target_aspect:
-        # Resize the image to match the target height, maintaining aspect ratio
         new_height = output_size[1]
         new_width = int(new_height * image_aspect)
         resized_image = image.resize((new_width, new_height), Image.LANCZOS)
-        # Calculate coordinates for cropping
         left = (new_width - output_size[0]) / 2
         top = 0
         right = (new_width + output_size[0]) / 2
         bottom = output_size[1]
     else:
-        # Resize the image to match the target width, maintaining aspect ratio
         new_width = output_size[0]
         new_height = int(new_width / image_aspect)
         resized_image = image.resize((new_width, new_height), Image.LANCZOS)
-        # Calculate coordinates for cropping
         left = 0
         top = (new_height - output_size[1]) / 2
         right = output_size[0]
         bottom = (new_height + output_size[1]) / 2
 
-    # Crop the image
     cropped_image = resized_image.crop((left, top, right, bottom))
     return cropped_image
 
 with gr.Blocks() as demo:
-  gr.Markdown('''# Community demo for Stable Video Diffusion - Img2Vid - XT ([model](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt), [paper](https://stability.ai/research/stable-video-diffusion-scaling-latent-video-diffusion-models-to-large-datasets), [stability's ui waitlist](https://stability.ai/contact))
-#### Research release ([_non-commercial_](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt/blob/main/LICENSE)): generate `4s` vid from a single image at (`25 frames` at `6 fps`). this demo uses [🧨 diffusers for low VRAM and fast generation](https://huggingface.co/docs/diffusers/main/en/using-diffusers/svd).
-  ''')
   with gr.Row():
       with gr.Column():
           image = gr.Image(label="Upload your image", type="pil")