Add more options, from the most useful to the least one (#10)

- Add more options, from the most useful to the least one (01ac1c081925b409a4a920d2f7e69271e14e07d1)


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

app.py

@@ -1,5 +1,4 @@
 import gradio as gr
-#import gradio.helpers
 import torch
 import os
 from glob import glob
@@ -12,7 +11,6 @@ from PIL import Image
 
 import uuid
 import random
-from huggingface_hub import hf_hub_download
 import spaces
 
 pipe = StableVideoDiffusionPipeline.from_pretrained(
@@ -29,9 +27,9 @@ def sample(
     randomize_seed: bool = True,
     motion_bucket_id: int = 127,
     fps_id: int = 6,
+    noise_aug_strength: float = 0.1,
+    decoding_t: int = 3,
     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",
 ):
@@ -46,7 +44,7 @@ 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 = pipe(image, decode_chunk_size=decoding_t, generator=generator, motion_bucket_id=motion_bucket_id, noise_aug_strength=noise_aug_strength, num_frames=25).frames[0]
     export_to_video(frames, video_path, fps=fps_id)
     
     return video_path, frames, seed
@@ -60,7 +58,7 @@ def resize_image(image, output_size=(1024, 576)):
     if image.width == output_size[0] and image.height == output_size[1]:
         return image
 
-    # Resize then crop if the original image is larger
+    # Resize 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]
@@ -94,17 +92,21 @@ with gr.Blocks() as demo:
       with gr.Column():
           image = gr.Image(label="Upload your image", type="pil")
           with gr.Accordion("Advanced options", open=False):
+              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)
+              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)
+              noise_aug_strength = gr.Slider(label="Noise strength", info="The noise to add", value=0.1, minimum=0, maximum=1, step=0.1)
+              decoding_t = gr.Slider(label="Decoding", info="Number of frames decoded at a time; this eats more VRAM; reduce if necessary", value=3, minimum=1, maximum=5, step=1)
               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, gallery, seed], api_name="video")
+  generate_btn.click(fn=sample, inputs=[image, seed, randomize_seed, motion_bucket_id, fps_id, noise_aug_strength, decoding_t], outputs=[video, gallery, seed], api_name="video")
 
 if __name__ == "__main__":
     demo.launch(share=True, show_api=False)