Update app.py

app.py

@@ -11,14 +11,15 @@ import uuid
 import random
 from huggingface_hub import hf_hub_download
 import spaces
+from tqdm import tqdm
+
+max_64_bit_int = 2**63 - 1
 
 pipe = StableVideoDiffusionPipeline.from_pretrained(
     "vdo/stable-video-diffusion-img2vid-xt-1-1", torch_dtype=torch.float16, variant="fp16"
 )
 pipe.to("cpu")
 
-max_64_bit_int = 2**63 - 1
-
 @spaces.GPU(duration=120)
 def sample(
     image: Image,
@@ -31,6 +32,7 @@ def sample(
     decoding_t: int = 3,  
     device: str = "cuda",
     output_folder: str = "outputs",
+    progress: gr.Progress,
 ):
     if image.mode == "RGBA":
         image = image.convert("RGB")
@@ -43,12 +45,18 @@ def sample(
     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]
+    frames = []
+    for i in tqdm(range(25), desc="Generando frames"):
+        frame = pipe(image, decode_chunk_size=decoding_t, generator=generator, motion_bucket_id=motion_bucket_id, noise_aug_strength=0.1, num_frames=1).frames[0]
+        frames.extend(frame)
+        progress.update(i/25)
+
     export_to_video(frames, video_path, fps=fps_id)
     torch.manual_seed(seed)
     
     return video_path, frames, seed
 
+
 def resize_image(image, output_size=(1024, 576)):
     target_aspect = output_size[0] / output_size[1]  
     image_aspect = image.width / image.height  
@@ -73,6 +81,7 @@ def resize_image(image, output_size=(1024, 576)):
     cropped_image = resized_image.crop((left, top, right, bottom))
     return cropped_image
 
+
 with gr.Blocks() as demo:
   with gr.Row():
       with gr.Column():
@@ -86,9 +95,11 @@ with gr.Blocks() as demo:
       with gr.Column():
           video = gr.Video(label="Generated video")
           gallery = gr.Gallery(label="Generated frames")
+          progress = gr.Progress(label="Progress")
       
   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, gallery, seed], api_name="video")
+  generate_btn.click(fn=sample, inputs=[image, seed, randomize_seed, motion_bucket_id, fps_id, "svd_xt", 0.02, 3, "cuda", "outputs", progress], outputs=[video, gallery, seed, progress], api_name="video")
+
 
 if __name__ == "__main__":
     demo.launch(share=True, show_api=False)