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 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, randomize_seed: bool, seed: int, randomize_cfg: bool, text_cfg_scale: float, image_cfg_scale: float, ): seed = random.randint(0, 100000) if randomize_seed else seed text_cfg_scale = round(random.uniform(6.0, 9.0), ndigits=2) if randomize_cfg else text_cfg_scale image_cfg_scale = round(random.uniform(1.2, 1.8), ndigits=2) if randomize_cfg else image_cfg_scale 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] 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) pix2pix_img = pix2pix(pil_i, prompt, 50, False, seed_in, False, 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 = """

Pix2Pix Video

Apply Instruct Pix2Pix Diffusion to a video

""" article = """

You may also like:

""" 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(): seed_inp = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, value=123456) trim_in = gr.Slider(label="Cut video at (s)", minimun=1, maximum=5, step=1, value=1) with gr.Column(): video_out = gr.Video(label="Pix2pix video result", elem_id="video-output") gr.HTML(""" Duplicate Space work with longer videos / skip the queue: """, elem_id="duplicate-container") submit_btn = gr.Button("Generate Pix2Pix 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,seed_inp, trim_in] outputs = [video_out, share_group] #ex = gr.Examples( # [ # ["Make it a marble sculpture", "./examples/pexels-jill-burrow-7665249_512x512.mp4", 422112651, 4], # ["Make it molten lava", "./examples/Ocean_Pexels_ 8953474_512x512.mp4", 43571876, 4] # ], # inputs=inputs, # outputs=outputs, # fn=infer, # cache_examples=True, #) gr.HTML(article) submit_btn.click(infer, inputs, outputs) share_button.click(None, [], [], _js=share_js) demo.queue(max_size=12).launch()