import gradio as gr import numpy as np import time import math import random import torch import spaces from diffusers import StableDiffusionXLInpaintPipeline from PIL import Image import PIL.ImageOps from pillow_heif import register_heif_opener register_heif_opener() max_64_bit_int = np.iinfo(np.int32).max if torch.cuda.is_available(): device = "cuda" floatType = torch.float16 variant = "fp16" else: device = "cpu" floatType = torch.float32 variant = None pipe = StableDiffusionXLInpaintPipeline.from_pretrained("diffusers/stable-diffusion-xl-1.0-inpainting-0.1", torch_dtype = floatType, variant = variant) pipe = pipe.to(device) default_local_storage = { "prompt": "", "negative_prompt": "Ugly, malformed, noise, blur, watermark", "num_inference_steps": 25, "guidance_scale": 7, "image_guidance_scale": 1.1, "strength": 0.99, "denoising_steps": 1000, "randomize_seed": True, "seed": random.randint(0, max_64_bit_int), "debug_mode": False } def save_preferences_prompt(preferences, value): preferences["prompt"] = value return preferences def save_preferences_negative_prompt(preferences, value): preferences["negative_prompt"] = value return preferences def save_preferences_num_inference_steps(preferences, value): preferences["num_inference_steps"] = value return preferences def save_preferences_guidance_scale(preferences, value): preferences["guidance_scale"] = value return preferences def save_preferences_image_guidance_scale(preferences, value): preferences["image_guidance_scale"] = value return preferences def save_preferences_strength(preferences, value): preferences["strength"] = value return preferences def save_preferences_denoising_steps(preferences, value): preferences["denoising_steps"] = value return preferences def save_preferences_randomize_seed(preferences, value): preferences["randomize_seed"] = value return preferences def save_preferences_seed(preferences, value): preferences["seed"] = value return preferences def save_preferences_debug_mode(preferences, value): preferences["debug_mode"] = value return preferences def load_preferences(saved_prefs): saved_prefs = init_preferences(saved_prefs) return [ saved_prefs["prompt"], saved_prefs["negative_prompt"], saved_prefs["num_inference_steps"], saved_prefs["guidance_scale"], saved_prefs["image_guidance_scale"], saved_prefs["strength"], saved_prefs["denoising_steps"], saved_prefs["randomize_seed"], saved_prefs["seed"], saved_prefs["debug_mode"] ] def init_preferences(saved_prefs): if saved_prefs is None: saved_prefs = default_local_storage return saved_prefs def update_seed(is_randomize_seed, seed): if is_randomize_seed: return random.randint(0, max_64_bit_int) return seed def toggle_debug(is_debug_mode): return [gr.update(visible = True)] + [gr.update(visible = is_debug_mode)] * 2 def check( source_img, prompt, uploaded_mask: Image.Image, negative_prompt, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, is_randomize_seed, seed, debug_mode, 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 inpaint( source_img, prompt, uploaded_mask: Image.Image, negative_prompt, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, is_randomize_seed, seed, debug_mode, progress = gr.Progress() ): check( source_img, prompt, uploaded_mask, negative_prompt, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, is_randomize_seed, seed, debug_mode ) start = time.time() progress(0, desc = "Preparing data...") if negative_prompt is None: negative_prompt = "" if num_inference_steps is None: num_inference_steps = 25 if guidance_scale is None: guidance_scale = 7 if image_guidance_scale is None: image_guidance_scale = 1.1 if strength is None: strength = 0.99 if denoising_steps is None: denoising_steps = 1000 if seed is None: seed = random.randint(0, max_64_bit_int) random.seed(seed) #pipe = pipe.manual_seed(seed) input_image = source_img["background"].convert("RGB") original_height, original_width, original_channel = np.array(input_image).shape output_width = original_width output_height = original_height if uploaded_mask is None: mask_image = source_img["layers"][0].convert("RGB") else: mask_image = uploaded_mask.convert("RGB") mask_image = mask_image.resize((original_width, original_height)) # Limited to 1 million pixels if 1024 * 1024 < output_width * output_height: factor = ((1024 * 1024) / (output_width * output_height))**0.5 process_width = math.floor(output_width * factor) process_height = math.floor(output_height * factor) limitation = " Due to technical limitation, the image have been downscaled and then upscaled."; else: process_width = output_width process_height = output_height limitation = ""; # Width and height must be multiple of 8 if (process_width % 8) != 0 or (process_height % 8) != 0: if ((process_width - (process_width % 8) + 8) * (process_height - (process_height % 8) + 8)) <= (1024 * 1024): process_width = process_width - (process_width % 8) + 8 process_height = process_height - (process_height % 8) + 8 elif (process_height % 8) <= (process_width % 8) and ((process_width - (process_width % 8) + 8) * process_height) <= (1024 * 1024): process_width = process_width - (process_width % 8) + 8 process_height = process_height - (process_height % 8) elif (process_width % 8) <= (process_height % 8) and (process_width * (process_height - (process_height % 8) + 8)) <= (1024 * 1024): process_width = process_width - (process_width % 8) process_height = process_height - (process_height % 8) + 8 else: process_width = process_width - (process_width % 8) process_height = process_height - (process_height % 8) if torch.cuda.is_available(): progress(None, desc = "Searching a GPU...") output_image = inpaint_on_gpu( seed, process_width, process_height, prompt, negative_prompt, input_image, mask_image, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, progress ) if limitation != "": output_image = output_image.resize((output_width, output_height)) if debug_mode == False: input_image = None mask_image = None end = time.time() secondes = int(end - start) minutes = math.floor(secondes / 60) secondes = secondes - (minutes * 60) hours = math.floor(minutes / 60) minutes = minutes - (hours * 60) return [ output_image, ("Start again to get a different result. " if is_randomize_seed else "") + "The image has been generated in " + ((str(hours) + " h, ") if hours != 0 else "") + ((str(minutes) + " min, ") if hours != 0 or minutes != 0 else "") + str(secondes) + " sec." + limitation, input_image, mask_image ] def inpaint_on_gpu2( seed, process_width, process_height, prompt, negative_prompt, input_image, mask_image, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, progress ): return input_image @spaces.GPU(duration=420) def inpaint_on_gpu( seed, process_width, process_height, prompt, negative_prompt, input_image, mask_image, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, progress ): progress(None, desc = "Processing...") return pipe( seeds = [seed], width = process_width, height = process_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, strength = strength, denoising_steps = denoising_steps, show_progress_bar = True ).images[0] with gr.Blocks() as interface: local_storage = gr.BrowserState(default_local_storage) gr.HTML( """

Inpaint / Outpaint

Modifies one detail of your image, at any resolution, freely, without account, without watermark, without installation, which can be downloaded



✨ Powered by SDXL 1.0 artificial intellingence. For illustration purpose, not information purpose. The new content is not based on real information but imagination.

""" + ("🏃‍♀️ Estimated time: few minutes. Current device: GPU." if torch.cuda.is_available() else "🐌 Slow process... ~1 hour. Current device: CPU.") + """ You can duplicate this space on a free account, it's designed to work on CPU, GPU and ZeroGPU.

⚖️ You can use, modify and share the generated images but not for commercial uses. """ ) with gr.Column(): source_img = gr.ImageMask(label = "Your image (click on the landscape 🌄 to upload your image; click on the pen 🖌️ to draw the mask)", type = "pil", brush=gr.Brush(colors=["#FFFFFF80"], color_mode="fixed")) prompt = gr.Textbox(label = "Prompt", info = "Describe the subject, the background and the style of image; 77 token limit", placeholder = "Describe what you want to see in the entire image", lines = 2) with gr.Accordion("Upload a mask", open = False): uploaded_mask = gr.Image(label = "Already made mask (black pixels will be preserved, white pixels will be redrawn)", sources = ["upload"], type = "pil") with gr.Accordion("Advanced options", open = False): negative_prompt = gr.Textbox(label = "Negative prompt", placeholder = "Describe what you do NOT want to see in the entire image", value = "Ugly, malformed, noise, blur, watermark") num_inference_steps = gr.Slider(minimum = 10, maximum = 100, value = 25, step = 1, label = "Number of inference steps", info = "lower=faster, higher=image quality") guidance_scale = gr.Slider(minimum = 1, maximum = 13, value = 7, step = 0.1, label = "Guidance Scale", info = "lower=image quality, higher=follow the prompt") image_guidance_scale = gr.Slider(minimum = 1, value = 1.1, step = 0.1, label = "Image Guidance Scale", info = "lower=image quality, higher=follow the image") strength = gr.Slider(value = 0.99, minimum = 0.01, maximum = 1.0, step = 0.01, label = "Strength", info = "lower=follow the original area, higher=redraw from scratch") denoising_steps = gr.Number(minimum = 0, value = 1000, step = 1, label = "Denoising", info = "lower=irrelevant result, higher=relevant result") randomize_seed = gr.Checkbox(label = "\U0001F3B2 Randomize seed", value = True, info = "If checked, result is always different") seed = gr.Slider(minimum = 0, maximum = max_64_bit_int, step = 1, randomize = True, label = "Seed") debug_mode = gr.Checkbox(label = "Debug mode", value = False, info = "Show intermediate results") submit = gr.Button("🚀 Inpaint/Outpaint", variant = "primary") warning = gr.HTML(value = "
Your computer must not enter into standby mode. On Chrome, you can force to keep a tab alive in chrome://discards/ The generation time may vary on the number of steps and the resolution of the image.
", visible = False) inpainted_image = gr.Image(label = "Inpainted image") information = gr.HTML() original_image = gr.Image(label = "Original image", visible = False) mask_image = gr.Image(label = "Mask image", visible = False) submit.click(update_seed, inputs = [ randomize_seed, seed ], outputs = [ seed ], queue = False, show_progress = False).then(toggle_debug, debug_mode, [ warning, original_image, mask_image ], queue = False, show_progress = False).then(check, inputs = [ source_img, prompt, uploaded_mask, negative_prompt, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, randomize_seed, seed, debug_mode ], outputs = [], queue = False, show_progress = False).success(inpaint, inputs = [ source_img, prompt, uploaded_mask, negative_prompt, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, randomize_seed, seed, debug_mode ], outputs = [ inpainted_image, information, original_image, mask_image ], scroll_to_output = True) prompt.change(fn = save_preferences_prompt, inputs = [ local_storage, prompt, ], outputs = [ local_storage ]) negative_prompt.change(fn = save_preferences_negative_prompt, inputs = [ local_storage, negative_prompt, ], outputs = [ local_storage ]) num_inference_steps.change(fn = save_preferences_num_inference_steps, inputs = [ local_storage, num_inference_steps, ], outputs = [ local_storage ]) guidance_scale.change(fn = save_preferences_guidance_scale, inputs = [ local_storage, guidance_scale, ], outputs = [ local_storage ]) image_guidance_scale.change(fn = save_preferences_image_guidance_scale, inputs = [ local_storage, image_guidance_scale, ], outputs = [ local_storage ]) strength.change(fn = save_preferences_strength, inputs = [ local_storage, strength, ], outputs = [ local_storage ]) denoising_steps.change(fn = save_preferences_denoising_steps, inputs = [ local_storage, denoising_steps, ], outputs = [ local_storage ]) randomize_seed.change(fn = save_preferences_randomize_seed, inputs = [ local_storage, randomize_seed, ], outputs = [ local_storage ]) seed.change(fn = save_preferences_seed, inputs = [ local_storage, seed, ], outputs = [ local_storage ]) debug_mode.change(fn = save_preferences_debug_mode, inputs = [ local_storage, debug_mode, ], outputs = [ local_storage ]) gr.Examples( fn = inpaint, inputs = [ source_img, prompt, uploaded_mask, negative_prompt, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, randomize_seed, seed, debug_mode ], outputs = [ inpainted_image, information, original_image, mask_image ], examples = [ [ "./Examples/Example1.png", "A deer, in a forest landscape, ultrarealistic, realistic, photorealistic, 8k", "./Examples/Mask1.webp", "Ugly, malformed, painting, drawing, cartoon, anime, 3d, noise, blur, watermark", 25, 7, 1.1, 0.99, 1000, False, 42, False ], [ "./Examples/Example3.jpg", "An angry old woman, ultrarealistic, realistic, photorealistic, 8k", "./Examples/Mask3.gif", "Ugly, malformed, painting, drawing, cartoon, anime, 3d, noise, blur, watermark", 25, 7, 1.5, 0.99, 1000, False, 42, False ], [ "./Examples/Example4.gif", "A laptop, ultrarealistic, realistic, photorealistic, 8k", "./Examples/Mask4.bmp", "Ugly, malformed, painting, drawing, cartoon, anime, 3d, noise, blur, watermark", 25, 7, 1.1, 0.99, 1000, False, 42, False ], [ "./Examples/Example5.bmp", "A sand castle, ultrarealistic, realistic, photorealistic, 8k", "./Examples/Mask5.png", "Ugly, malformed, painting, drawing, cartoon, anime, 3d, noise, blur, watermark", 50, 7, 1.5, 0.5, 1000, False, 42, False ], [ "./Examples/Example2.webp", "A cat, ultrarealistic, realistic, photorealistic, 8k", "./Examples/Mask2.png", "Ugly, malformed, painting, drawing, cartoon, anime, 3d, noise, blur, watermark", 25, 7, 1.1, 0.99, 1000, False, 42, False ], [ "./Examples/Example6.webp", "A car, in the street, in a city, photorealistic, realistic, extremely detailled, 8k", "./Examples/Mask6.webp", "Ugly, malformed, painting, drawing, cartoon, anime, 3d, noise, blur, watermark, forest, wood, trees", 25, 7, 1.1, 0.99, 1000, False, 42, False ], ], cache_examples = False, ) gr.Markdown( """ ## How to prompt your image To easily read your prompt, start with the subject, then describ the pose or action, then secondary elements, then the background, then the graphical style, then the image quality: ``` A Vietnamese woman, red clothes, walking, smilling, in the street, a car on the left, in a modern city, photorealistic, 8k ``` You can use round brackets to increase the importance of a part: ``` A Vietnamese woman, (red clothes), walking, smilling, in the street, a car on the left, in a modern city, photorealistic, 8k ``` You can use several levels of round brackets to even more increase the importance of a part: ``` A Vietnamese woman, ((red clothes)), (walking), smilling, in the street, a car on the left, in a modern city, photorealistic, 8k ``` You can use number instead of several round brackets: ``` A Vietnamese woman, (red clothes:1.5), (walking), smilling, in the street, a car on the left, in a modern city, photorealistic, 8k ``` You can do the same thing with square brackets to decrease the importance of a part: ``` A [Vietnamese] woman, (red clothes:1.5), (walking), smilling, in the street, a car on the left, in a modern city, photorealistic, 8k ``` To easily read your negative prompt, organize it the same way as your prompt (not important for the AI): ``` man, boy, hat, running, tree, bicycle, forest, drawing, painting, cartoon, 3d, monochrome, blurry, noisy, bokeh ``` """ ) # Load saved preferences when the page loads interface.load( fn=load_preferences, inputs = [ local_storage ], outputs = [ prompt, negative_prompt, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, randomize_seed, seed, debug_mode ] ) interface.queue().launch()