Application creation

app.py

@@ -0,0 +1,250 @@
+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,
+    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,
+    randomize_seed,
+    seed,
+    progress = gr.Progress()):
+    check(
+        source_img,
+        prompt,
+        negative_prompt,
+        denoising_steps,
+        num_inference_steps,
+        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 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...).")
+
+    output_height, output_width, dummy_channel = np.array(input_image).shape
+    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.";
+
+    # 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,
+        denoising_steps = denoising_steps,
+        show_progress_bar = True
+    ).images[0]
+
+    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(
+        """
+        <p style="text-align: center;"><b><big><big><big>Instruct Pix2Pix demo</big></big></big></b></p>
+        <p style="text-align: center;">Modifies your image using a textual instruction, up to 1 million pixels, freely, without account, without watermark, without installation, which can be downloaded</p>
+        <br/>
+        <br/>
+        🚀 Powered by <i>SD 1.5</i> and <i>ControlNet</i>
+        <br/>
+        <ul>
+        <li>To change the <b>view angle</b> of your image, I recommend to use <i>Zero123</i>,</li>
+        <li>To <b>upscale</b> your image, I recommend to use <i>Ilaria Upscaler</i>,</li>
+        <li>To <b>slightly change</b> your image, I recommend to use <i>Image-to-Image SDXL</i>,</li>
+        <li>To change <b>one detail</b> on your image, I recommend to use <i>Inpaint SDXL</i>,</li>
+        <li>To remove the <b>background</b> of your image, I recommend to use <i>BRIA</i>,</li>
+        <li>To enlarge the <b>viewpoint</b> of your image, I recommend to use <i>Uncrop</i>,</li>
+        <li>To make a <b>tile</b> of your image, I recommend to use <i>Make My Image Tile</i>,</li>
+        </ul>
+        <br/>
+        🐌 Slow process... ~1 hour. If this space does not work or you want a faster run, use <i>Instruct Pix2Pix</i> available on terrapretapermaculture's <i>ControlNet-v1-1</i> space (last tab) or on <i>Dezgo</i> site.<br>You can duplicate this space on a free account, it works on CPU.<br/>
+        <a href='https://huggingface.co/spaces/Fabrice-TIERCELIN/Instruct-Pix2Pix?duplicate=true'><img src='https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14'></a>
+        <br/>
+        ⚖️ You can use, modify and share the generated images but not for commercial uses.
+        """
+    )
+    with gr.Column():
+        source_img = gr.Image(label = "Your image", sources = ["upload"], type = "numpy")
+        prompt = gr.Textbox(label = 'Prompt', info = "Instruct what to change in the image", placeholder = 'Order the AI what to change in the image')
+        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 image', value = 'Watermark')
+            denoising_steps = gr.Slider(minimum = 0, maximum = 1000, value = 0, step = 1, label = "Denoising", info = "lower=irrelevant result, higher=relevant result")
+            num_inference_steps = gr.Slider(minimum = 10, maximum = 25, value = 20, step = 1, label = "Number of inference steps", info = "lower=faster, higher=image quality")
+            guidance_scale = gr.Slider(minimum = 1, maximum = 13, value = 5, step = 0.1, label = "Classifier-Free Guidance Scale", info = "lower=image quality, higher=follow the prompt")
+            randomize_seed = gr.Checkbox(label = "\U0001F3B2 Randomize seed (not working, always checked)", 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 (if not randomized)")
+
+        submit = gr.Button("Modify", variant = "primary")
+
+        modified_image = gr.Image(label = "Modified image")
+        information = gr.Label(label = "Information")
+
+    submit.click(check, inputs = [
+        source_img,
+        prompt,
+        negative_prompt,
+        denoising_steps,
+        num_inference_steps,
+        guidance_scale,
+        randomize_seed,
+        seed
+    ], outputs = [], queue = False, show_progress = False).success(pix2pix, inputs = [
+        source_img,
+        prompt,
+        negative_prompt,
+        denoising_steps,
+        num_inference_steps,
+        guidance_scale,
+        randomize_seed,
+        seed
+    ], outputs = [
+        modified_image,
+        information
+    ], scroll_to_output = True)
+
+    gr.Examples(
+	    inputs = [
+            source_img,
+            prompt,
+            negative_prompt,
+            denoising_steps,
+            num_inference_steps,
+            guidance_scale,
+            randomize_seed,
+            seed
+        ],
+	    outputs = [
+            modified_image,
+            information
+        ],
+        examples = [
+                [
+                    "Example1.webp",
+                    "What if it's snowing?",
+                    "Watermark",
+                    1,
+                    20,
+                    5,
+                    True,
+                    42
+                ],
+                [
+                    "Example2.png",
+                    "What if this woman had brown hair?",
+                    "Watermark",
+                    1,
+                    20,
+                    5,
+                    True,
+                    42
+                ],
+                [
+                    "Example3.jpeg",
+                    "Replace the house by a windmill",
+                    "Watermark",
+                    1,
+                    20,
+                    5,
+                    True,
+                    42
+                ],
+            ],
+        cache_examples = False,
+    )
+
+    interface.queue().launch()