newtest

app.py

@@ -1,116 +1,47 @@
-import gradio as gr
-import spaces
-#import gradio.helpers
 import torch
-import os
-from glob import glob
-from pathlib import Path
-from typing import Optional
-
+import gradio as gr
 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
+import spaces
 
 # Check if GPU is available
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-# Load the pipeline with authentication token
-pipe = StableVideoDiffusionPipeline.from_pretrained(
-    "stabilityai/stable-video-diffusion-img2vid-xt",
-    torch_dtype=torch.float16,
-    variant="fp16"
+# Load the pipeline
+pipeline = 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
+pipeline.to(device)
 
 @spaces.GPU(duration=120)
-def sample(
-    image: Image,
-    seed: Optional[int] = 42,
-    randomize_seed: bool = True,
-    motion_bucket_id: int = 127,
-    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.
-    device: str = "cuda",
-    output_folder: str = "outputs",
-    progress=gr.Progress(track_tqdm=True)
-):
-    if image.mode == "RGBA":
-        image = image.convert("RGB")
-        
-    if randomize_seed:
-        seed = random.randint(0, max_64_bit_int)
-    generator = torch.manual_seed(seed)
-    
-    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_to_video(frames, video_path, fps=fps_id)
-    torch.manual_seed(seed)
-    
-    return video_path, 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
-
-    # 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")
-        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)
-      motion_bucket_id = gr.Slider(label="Motion bucket id", info="Controls how much motion to add/remove from the image", value=127, minimum=1, maximum=255)
-      fps_id = gr.Slider(label="Frames per second", info="The length of your video in seconds will be 25/fps", value=6, minimum=5, maximum=30)
-      
-  image.upload(fn=resize_image, inputs=image, outputs=image, queue=False)
-  generate_btn.click(fn=sample, inputs=[image, seed, randomize_seed, motion_bucket_id, fps_id], outputs=[video, seed], api_name="video")
-  
+def generate_video(image_path, seed):
+    # Load and preprocess the image
+    image = load_image(image_path)
+    image = image.resize((1024, 576))
+
+    # Set the generator seed
+    generator = torch.Generator(device=device).manual_seed(seed)
+
+    # Generate the video frames
+    frames = pipeline(image, decode_chunk_size=8, generator=generator).frames[0]
+
+    # Export the frames to a video file
+    output_video_path = "generated.mp4"
+    export_to_video(frames, output_video_path, fps=7)
+
+    return output_video_path
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=generate_video,
+    inputs=[
+        gr.Image(type="filepath", label="Upload Image"),
+        gr.Number(label="Seed", value=42)
+    ],
+    outputs=gr.Video(label="Generated Video"),
+    title="Stable Video Diffusion",
+    description="Generate a video from an uploaded image using Stable Video Diffusion.",
+)
 
-if __name__ == "__main__":
-    #demo.queue(max_size=20, api_open=False)
-    demo.launch(share=True, show_api=False)
+# Launch the interface
+iface.launch()