Reuse the code from a working space (2/2) (#8)

- Reuse the code from a working space (2/2) (7c6fe62db5a01b7ff46f700df71b29e9dd548aae)


Co-authored-by: Fabrice TIERCELIN <[email protected]>

app.py

@@ -1,4 +1,5 @@
 import gradio as gr
+#import gradio.helpers
 import torch
 import os
 from glob import glob
@@ -11,18 +12,17 @@ from PIL import Image
 
 import uuid
 import random
-import spaces
 from huggingface_hub import hf_hub_download
+import spaces
 
 pipe = StableVideoDiffusionPipeline.from_pretrained(
     "vdo/stable-video-diffusion-img2vid-xt-1-1", torch_dtype=torch.float16, variant="fp16"
 )
 pipe.to("cuda")
-pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
 
 max_64_bit_int = 2**63 - 1
 
-@spaces.GPU(duration=250)
+@spaces.GPU(duration=120)
 def sample(
     image: Image,
     seed: Optional[int] = 42,
@@ -50,7 +50,7 @@ def sample(
     export_to_video(frames, video_path, fps=fps_id)
     torch.manual_seed(seed)
     
-    return video_path, seed
+    return video_path, frames, seed
 
 def resize_image(image, output_size=(1024, 576)):
     # Calculate aspect ratios
@@ -84,22 +84,24 @@ def resize_image(image, output_size=(1024, 576)):
     return cropped_image
 
 with gr.Blocks() as demo:
-  gr.Markdown('''# Stable Video Diffusion
+  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)
+      with gr.Column():
+          image = gr.Image(label="Upload your image", type="pil")
+          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)
+          generate_btn = gr.Button(value="Animate", variant="primary")
+      with gr.Column():
+          video = gr.Video(label="Generated video")
+          gallery = gr.Gallery(label="Generated frames")
       
   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")
+  generate_btn.click(fn=sample, inputs=[image, seed, randomize_seed, motion_bucket_id, fps_id], outputs=[video, gallery, seed], api_name="video")
 
 if __name__ == "__main__":
-    demo.queue(max_size=20, api_open=False)
     demo.launch(share=True, show_api=False)