from __future__ import annotations import gradio as gr import os import cv2 import numpy as np from PIL import Image from moviepy.editor import * from share_btn import community_icon_html, loading_icon_html, share_js import pathlib import shlex import subprocess if os.getenv('SYSTEM') == 'spaces': with open('patch') as f: subprocess.run(shlex.split('patch -p1'), stdin=f, cwd='ControlNet') base_url = 'https://huggingface.co/lllyasviel/ControlNet/resolve/main/annotator/ckpts/' names = [ 'body_pose_model.pth', 'dpt_hybrid-midas-501f0c75.pt', 'hand_pose_model.pth', 'mlsd_large_512_fp32.pth', 'mlsd_tiny_512_fp32.pth', 'network-bsds500.pth', 'upernet_global_small.pth', ] for name in names: command = f'wget https://huggingface.co/lllyasviel/ControlNet/resolve/main/annotator/ckpts/{name} -O {name}' out_path = pathlib.Path(f'ControlNet/annotator/ckpts/{name}') if out_path.exists(): continue subprocess.run(shlex.split(command), cwd='ControlNet/annotator/ckpts/') from model import Model model = Model() def controlnet(i, prompt, seed_in): a_prompt = "best quality, extremely detailed" n_prompt = "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality" num_samples = 1 image_resolution = 512 detect_resolution = 512 ddim_steps = 20 scale = 9.0 eta = 0.0 result = model.process_pose(i, prompt, a_prompt, n_prompt, num_samples, image_resolution, detect_resolution, ddim_steps, scale, seed_in, eta) print(result) return 'done' 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, seed_in, trim_value): print(f""" ——————————————— {prompt} ———————————————""") # 1. break video into frames and get FPS 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) # 2. prepare frames result array result_frames = [] print("set stop frames to: " + str(n_frame)) for i in frames_list[0:int(n_frame)]: controlnet_img = controlnet(i, prompt, seed_in) #images = controlnet_img[0] #rgb_im = images[0].convert("RGB") # exporting the image #rgb_im.save(f"result_img-{i}.jpg") #result_frames.append(f"result_img-{i}.jpg") #print("frame " + i + "/" + str(n_frame) + ": done;") #final_vid = create_video(result_frames, fps) print("finished !") #return final_vid, gr.Group.update(visible=True) return controlnet_img title = """
Apply Instruct Pix2Pix Diffusion to a video
You may also like: