Update app.py

app.py

@@ -1,28 +1,22 @@
 import gradio as gr
-#import gradio.helpers
 import torch
 import os
+import uuid
+import random
+
 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
 
-#gradio.helpers.CACHED_FOLDER = '/data/cache'
-
 pipe = StableVideoDiffusionPipeline.from_pretrained(
     "stabilityai/stable-video-diffusion-img2vid-xt", torch_dtype=torch.float16, variant="fp16"
 )
 pipe.to("cuda")
 pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
-#pipe.vae = torch.compile(pipe.vae, mode="reduce-overhead", fullgraph=True)
-
 max_64_bit_int = 2**63 - 1
 
 def sample(
@@ -39,19 +33,22 @@ def sample(
 ):
     if image.mode == "RGBA":
         image = image.convert("RGB")
-        
     if(randomize_seed):
         seed = random.randint(0, max_64_bit_int)
     generator = torch.manual_seed(seed)
-    
+
+    # Count completed mp4 videos and set the path
     os.makedirs(output_folder, exist_ok=True)
     base_count = len(glob(os.path.join(output_folder, "*.mp4")))
     video_path = os.path.join(output_folder, f"{base_count:06d}.mp4")
 
     frames = pipe(image, decode_chunk_size=decoding_t, generator=generator, motion_bucket_id=motion_bucket_id, noise_aug_strength=0.1, num_frames=25).frames[0]
+
+    # Export frames to video
     export_to_video(frames, video_path, fps=fps_id)
     torch.manual_seed(seed)
-    
+
+    # Return the video and seed
     return video_path, seed
 
 def resize_image(image, output_size=(1024, 576)):
@@ -65,6 +62,7 @@ def resize_image(image, output_size=(1024, 576)):
         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
@@ -75,6 +73,7 @@ def resize_image(image, output_size=(1024, 576)):
         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
@@ -86,14 +85,18 @@ def resize_image(image, output_size=(1024, 576)):
     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).
+  gr.Markdown('''# Stable Video Diffusion using Image 2 Video 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")
         generate_btn = gr.Button("Generate")
     video = gr.Video()
+      
   with gr.Accordion("Advanced options", open=False):
       seed = gr.Slider(label="Seed", value=42, randomize=True, minimum=0, maximum=max_64_bit_int, step=1)
       randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
@@ -104,15 +107,15 @@ with gr.Blocks() as demo:
   generate_btn.click(fn=sample, inputs=[image, seed, randomize_seed, motion_bucket_id, fps_id], outputs=[video, seed], api_name="video")
   gr.Examples(
     examples=[
-        "images/blink_meme.png",
-        "images/confused2_meme.png",
-        "images/disaster_meme.png",
-        "images/distracted_meme.png",
-        "images/hide_meme.png",
-        "images/nazare_meme.png",
-        "images/success_meme.png",
-        "images/willy_meme.png",
-        "images/wink_meme.png"
+        "images/01.png",
+        "images/02.png",
+        "images/03.png",
+        "images/04.png",
+        "images/05.png",
+        "images/06.png",
+        "images/07.png",
+        "images/08.png",
+        "images/09.png"
     ],
     inputs=image,
     outputs=[video, seed],