from diffusers import ( ControlNetModel, DiffusionPipeline, StableDiffusionControlNetPipeline, ) import gradio as gr import numpy as np import os import time import math import random import imageio from PIL import Image, ImageFilter import torch max_64_bit_int = 2**63 - 1 device = "cuda" if torch.cuda.is_available() else "cpu" controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11e_sd15_ip2p", torch_dtype = torch.float32) pipe = StableDiffusionControlNetPipeline.from_pretrained( "runwayml/stable-diffusion-v1-5", safety_checker = None, controlnet = controlnet, torch_dtype = torch.float32 ) pipe = pipe.to(device) def check( source_img, prompt, negative_prompt, denoising_steps, num_inference_steps, guidance_scale, image_guidance_scale, randomize_seed, seed, progress = gr.Progress()): if source_img is None: raise gr.Error("Please provide an image.") if prompt is None or prompt == "": raise gr.Error("Please provide a prompt input.") def pix2pix( source_img, prompt, negative_prompt, denoising_steps, num_inference_steps, guidance_scale, image_guidance_scale, randomize_seed, seed, progress = gr.Progress()): check( source_img, prompt, negative_prompt, denoising_steps, num_inference_steps, guidance_scale, image_guidance_scale, randomize_seed, seed ) start = time.time() progress(0, desc = "Preparing data...") if negative_prompt is None: negative_prompt = "" if denoising_steps is None: denoising_steps = 0 if num_inference_steps is None: num_inference_steps = 20 if guidance_scale is None: guidance_scale = 5 if image_guidance_scale is None: image_guidance_scale = 1.5 if randomize_seed: seed = random.randint(0, max_64_bit_int) random.seed(seed) #pipe = pipe.manual_seed(seed) try: imageio.imwrite("data.png", source_img) except: raise gr.Error("Can't read input image. You can try to first save your image in another format (.webp, .png, .jpeg, .bmp...).") # Input image try: input_image = Image.open("data.png").convert("RGB") except: raise gr.Error("Can't open input image. You can try to first save your image in another format (.webp, .png, .jpeg, .bmp...).") original_height, original_width, dummy_channel = np.array(input_image).shape output_width = original_width output_height = original_height mask_image = Image.new(mode = input_image.mode, size = (output_width, output_height), color = "white") limitation = ""; # Limited to 1 million pixels if 1024 * 1024 < output_width * output_height: factor = ((1024 * 1024) / (output_width * output_height))**0.5 output_width = math.floor(output_width * factor) output_height = math.floor(output_height * factor) limitation = " Due to technical limitation, the image have been downscaled and then upscaled."; # Width and height must be multiple of 8 output_width = output_width - (output_width % 8) output_height = output_height - (output_height % 8) progress(None, desc = "Processing...") output_image = pipe( seeds=[seed], width = output_width, height = output_height, prompt = prompt, negative_prompt = negative_prompt, image = input_image, mask_image = mask_image, num_inference_steps = num_inference_steps, guidance_scale = guidance_scale, image_guidance_scale = image_guidance_scale, denoising_steps = denoising_steps, show_progress_bar = True ).images[0] if limitation != "": output_image = output_image.resize((original_width, original_height)) end = time.time() secondes = int(end - start) minutes = secondes // 60 secondes = secondes - (minutes * 60) hours = minutes // 60 minutes = minutes - (hours * 60) return [ output_image, "Start again to get a different result. The new image is " + str(output_width) + " pixels large and " + str(output_height) + " pixels high, so an image of " + f'{output_width * output_height:,}' + " pixels. The image have been generated in " + str(hours) + " h, " + str(minutes) + " min, " + str(secondes) + " sec." + limitation ] with gr.Blocks() as interface: gr.Markdown( """
Instruct Pix2Pix demo
Modifies your image using a textual instruction, up to 1 million pixels, freely, without account, without watermark, without installation, which can be downloaded