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 from diffusers import StableDiffusionInstructPix2PixPipeline import torch from PIL import Image, ImageOps import time import psutil import math import random pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained("timbrooks/instruct-pix2pix", torch_dtype=torch.float16, safety_checker=None) device = "GPU 🔥" if torch.cuda.is_available() else "CPU 🥶" if torch.cuda.is_available(): pipe = pipe.to("cuda") def pix2pix( input_image: Image.Image, instruction: str, steps: int, seed: int, text_cfg_scale: float, image_cfg_scale: float, ): width, height = input_image.size factor = 512 / max(width, height) factor = math.ceil(min(width, height) * factor / 64) * 64 / min(width, height) width = int((width * factor) // 64) * 64 height = int((height * factor) // 64) * 64 input_image = ImageOps.fit(input_image, (width, height), method=Image.Resampling.LANCZOS) if instruction == "": return [input_image, seed] generator = torch.manual_seed(seed) edited_image = pipe( instruction, image=input_image, guidance_scale=text_cfg_scale, image_guidance_scale=image_cfg_scale, num_inference_steps=steps, generator=generator, ).images[0] print(f"EDITED: {edited_image}") return edited_image 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(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)]: pil_i = Image.open(i).convert("RGB") pix2pix_img = pix2pix(pil_i, prompt, 50, seed_in, 7.5, 1.5) print(pix2pix_img) image = Image.open(pix2pix_img) rgb_im = image.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) title = """
Apply Instruct Pix2Pix Diffusion to a video
You may also like: