app.py

import gradio as gr
import os
import cv2
import numpy as np

from moviepy.editor import *
from share_btn import community_icon_html, loading_icon_html, share_js

xdecoder = gr.Interface.load(name="spaces/xdecoder/Instruct-X-Decoder")

def get_frames(video_in):
    frames = []
    #resize the video
    clip = VideoFileClip(video_in)
    
    #check fps
    if clip.fps > 30:
        print("vide rate is over 30, resetting to 30")
        clip_resized = clip.resize(height=512)
        clip_resized.write_videofile("video_resized.mp4", fps=30)
    else:
        print("video rate is OK")
        clip_resized = clip.resize(height=512)
        clip_resized.write_videofile("video_resized.mp4", fps=clip.fps)
    
    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)
    print("video fps: " + str(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, 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):
        print("video is shorter than the cut value")
        n_frame = len(frames_list)
    
    result_frames = []
    print("set stop frames to: " + str(n_frame))
    
    for i in frames_list[0:int(n_frame)]:
        xdecoder_img = xdecoder(i, prompt, fn_index=0)
        result_frames.append(xdecoder_img)
        print("frame " + i + "/" + str(n_frame) + ": done;")

    print(result_frames)
    final_vid = create_video(result_frames, fps)
    print("finished !")
    
    return final_vid, gr.Group.update(visible=True)

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;">
            Instruct X-Decoder Video
        </h1>
        </div>
        <p style="margin-bottom: 10px; font-size: 94%">
        Apply Instruct X-Decoder to a video <br />
        Note: this space loads the Instruct X-Decoder demo which is optimized to edit images<br />
        Inference time may be super slow, results might not be consistent between frames
        </p>
    </div>
"""

article = """
    
    <div class="footer">
        <p>
        Follow <a href="https://twitter.com/fffiloni" target="_blank">Sylvain Filoni</a> for future updates 🤗
        </p>
    </div>
    <div id="may-like-container" style="display: flex;justify-content: center;flex-direction: column;align-items: center;margin-bottom: 30px;">
        <p>You may also like: </p>
        <div id="may-like-content" style="display:flex;flex-wrap: wrap;align-items:center;height:20px;">
            
            <svg height="20" width="182" style="margin-left:4px;margin-bottom: 6px;">       
                 <a href="https://huggingface.co/spaces/xdecoder/Instruct-X-Decoder" target="_blank">
                    <image href="https://img.shields.io/badge/🤗 Spaces-Instruct_X•Decoder-blue" src="https://img.shields.io/badge/🤗 Spaces-Instruct_X•Decoder-blue.png" height="20"/>
                 </a>
            </svg>
            <svg height="20" width="148" style="margin-left:4px;margin-bottom: 6px;">       
                 <a href="https://huggingface.co/spaces/fffiloni/Pix2Pix-Video" target="_blank">
                    <image href="https://img.shields.io/badge/🤗 Spaces-Pix2Pix_Video-blue" src="https://img.shields.io/badge/🤗 Spaces-Pix2Pix_Video-blue.png" height="20"/>
                 </a>
            </svg>
            
        </div>
    
    </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():
                video_inp = gr.Video(label="Video source", source="upload", type="filepath", elem_id="input-vid")
                prompt = gr.Textbox(label="Prompt", placeholder="enter prompt", show_label=False, elem_id="prompt-in")
                with gr.Row():
                    trim_in = gr.Slider(label="Cut video at (s)", minimun=1, maximum=3, step=1, value=1, interactive=False)
            with gr.Column():
                video_out = gr.Video(label="Pix2pix video result", elem_id="video-output")
        
                submit_btn = gr.Button("Generate X-Decoder video")

                with gr.Group(elem_id="share-btn-container", visible=False) as share_group:
                    community_icon = gr.HTML(community_icon_html)
                    loading_icon = gr.HTML(loading_icon_html)
                    share_button = gr.Button("Share to community", elem_id="share-btn")
        
        inputs = [prompt, video_inp, trim_in]
        outputs = [video_out, share_group]
        
        gr.HTML(article)
    
    submit_btn.click(infer, inputs, outputs)
    share_button.click(None, [], [], _js=share_js)

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