app.py

import gradio as gr
import os
import cv2
import numpy as np
from moviepy.editor import *

token = os.environ.get('HF_TOKEN')
pix2pix = gr.Blocks.load(name="spaces/fffiloni/instruct-pix2pix-clone", api_key=token)

def get_frames(video_in):
    frames = []
    #resize the video
    clip = mp.VideoFileClip(video_in)
    clip_resized = clip.resize(height=512)
    clip_resized.write_videofile("video_resized.mp4")
    print("video resized to 512 height")
    
    # Opens the Video file with CV2
    cap= cv2.VideoCapture("video_resized.mp4")
    
    fps = cap.get(cv2.CAP_PROP_FPS)
    i=0
    while(cap.isOpened()):
        ret, frame = cap.read()
        if ret == False:
            break
        cv2.imwrite('kang'+str(i)+'.jpg',frame)
        frames.append('kang'+str(i)+'.jpg')
        i+=1
    
    cap.release()
    cv2.destroyAllWindows()
    print("broke the video into frames")
    return frames, fps

def create_video(frames, fps):
    print("building video result")
    clip = ImageSequenceClip(frames, fps=fps)
    clip.write_videofile("movie.mp4", fps=fps)
    
    return 'movie.mp4'


def infer(prompt,video_in, seed_in, trim_value):
    print(prompt)
    break_vid = get_frames(video_in)
    
    frames_list= break_vid[0]
    fps = break_vid[1]
    n_frame = int(trim_value*fps)
    if n_frame >= len(frames_list):
        n_frame = len(frames_list)
    result_frames = []
    print("set stop frames to: " + n_frame)
    for i in frames_list[0:int(n_frame)]:
        pix2pix_img = pix2pix(prompt,5.5,1.5,i,15,"",512,512,seed_in,fn_index=0)
        images = [os.path.join(pix2pix_img[0], img) for img in os.listdir(pix2pix_img[0])]
        result_frames.append(images[0])
        print("frame " + i + ": done;")

    final_vid = create_video(result_frames, fps)
    print("finished !")
    return final_vid

title = """
    <div style="text-align: center; max-width: 700px; margin: 0 auto;">
        <div
        style="
            display: inline-flex;
            align-items: center;
            gap: 0.8rem;
            font-size: 1.75rem;
        "
        >
        <h1 style="font-weight: 900; margin-bottom: 7px; margin-top: 5px;">
            Pix2Pix Video
        </h1>
        </div>
        <p style="margin-bottom: 10px; font-size: 94%">
        Apply Instruct Pix2Pix Diffusion to a video 
        </p>
    </div>
"""

article = """
    
    <div class="footer">
        <p>
         
        Follow <a href="https://twitter.com/fffiloni" target="_blank">Sylvain Filoni</a> for future updates 🤗
        </p>
    </div>
    
"""

with gr.Blocks(css='style.css') as demo:
    with gr.Column(elem_id="col-container"):
        gr.HTML(title)
        with gr.Row():
            with gr.Column():
                prompt = gr.Textbox(label="Prompt", placeholder="enter prompt", show_label=False)
                video_inp = gr.Video(label="Video source", source="upload", type="filepath")
                with gr.Row():
                    seed_inp = gr.Slider(minimum=0, maximum=10000, step=1, value=123456)
                    trim_in = gr.Slider(label="Cut video at (s)", minimun=2, maximum=10, step=1, value=2)
            with gr.Column():
                
                video_out = gr.Video(label="Pix2pix video result")
                submit_btn = gr.Button("Generate Pix2Pix video")
        gr.HTML(article)
    inputs = [prompt,video_inp,seed_inp, trim_in]
    outputs = [video_out]
    
    submit_btn.click(infer, inputs, outputs)

demo.launch().queue(max_size=12)