Create app.py

app.py

@@ -0,0 +1,327 @@
+import gradio as gr
+import numpy as np
+import time
+import math
+import random
+import torch
+
+from diffusers import AutoPipelineForImage2Image
+from PIL import Image, ImageFilter
+
+max_64_bit_int = 2**63 - 1
+
+# Automatic device detection
+if torch.cuda.is_available():
+    device = "cuda"
+    floatType = torch.float16
+    variant = "fp16"
+else:
+    device = "cpu"
+    floatType = torch.float32
+    variant = None
+
+pipe = AutoPipelineForImage2Image.from_pretrained("stabilityai/sdxl-turbo", torch_dtype = floatType, variant = variant)
+pipe = pipe.to(device)
+
+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 = is_debug_mode)]
+
+def check(
+    source_img,
+    prompt,
+    negative_prompt,
+    num_inference_steps,
+    guidance_scale,
+    image_guidance_scale,
+    strength,
+    denoising_steps,
+    seed,
+    is_randomize_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 redraw(
+    source_img,
+    prompt,
+    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,
+        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 = 0.5
+
+    if denoising_steps is None:
+        denoising_steps = 1000
+
+    if seed is None:
+        seed = random.randint(0, max_64_bit_int)
+
+    random.seed(seed)
+    torch.manual_seed(seed)
+
+    input_image = source_img.convert("RGB")
+
+    original_height, original_width, original_channel = np.array(input_image).shape
+    output_width = original_width
+    output_height = 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)
+
+    progress(None, desc = "Processing...")
+    output_image = pipe(
+        seeds = [seed],
+        width = process_width,
+        height = process_height,
+        prompt = prompt,
+        negative_prompt = negative_prompt,
+        image = input_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]
+
+    if limitation != "":
+        output_image = output_image.resize((output_width, output_height))
+
+    if debug_mode == False:
+        input_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
+    ]
+
+with gr.Blocks() as interface:
+    gr.HTML(
+        """
+        <h1 style="text-align: center;">Image-to-Image</h1>
+        <p style="text-align: center;">Modifies the global render of your image, at any resolution, freely, without account, without watermark, without installation, which can be downloaded</p>
+        <br/>
+        <br/>
+        ✨ Powered by <i>SDXL Turbo</i> artificial intellingence. For illustration purpose, not information purpose. The new content is not based on real information but imagination.
+        <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><a href="https://huggingface.co/spaces/Fabrice-TIERCELIN/SUPIR">SUPIR</a></i>,</li>
+        <li>To change one <b>detail</b> on your image, I recommend to use <i>Inpaint SDXL</i>,</li>
+        <li>If you need to enlarge the <b>viewpoint</b> of your image, I recommend you to use <i>Uncrop</i>,</li>
+        <li>To remove the <b>background</b> of your image, I recommend to use <i>BRIA</i>,</li>
+        <li>To make a <b>tile</b> of your image, I recommend to use <i>Make My Image Tile</i>,</li>
+        <li>To modify <b>anything else</b> on your image, I recommend to use <i>Instruct Pix2Pix</i>.</li>
+        </ul>
+        <br/>
+        🐌 Slow process... ~2 hours. Your computer must <u>not</u> enter into standby mode.<br/>You can duplicate this space on a free account, it works on CPU and should also run on CUDA.<br/>
+        <a href='https://huggingface.co/spaces/Fabrice-TIERCELIN/Image-to-Image?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", "webcam", "clipboard"], type = "pil")
+        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", lines = 2)
+        strength = gr.Slider(value = 0.5, minimum = 0.01, maximum = 1.0, step = 0.01, label = "Strength", info = "lower=follow the original image, higher=follow the prompt")
+        with gr.Accordion("Advanced options", open = False):
+             negative_prompt = gr.Textbox(label = "Negative prompt", placeholder = "Describe what you do NOT want to see", 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 = "Classifier-Free 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")
+             denoising_steps = gr.Slider(minimum = 0, maximum = 1000, 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("🚀 Redraw", variant = "primary")
+
+        redrawn_image = gr.Image(label = "Redrawn image")
+        information = gr.HTML()
+        original_image = gr.Image(label = "Original image", visible = False)
+
+    submit.click(update_seed, inputs = [
+        randomize_seed,
+        seed
+    ], outputs = [
+        seed
+    ], queue = False, show_progress = False).then(toggle_debug, debug_mode, [
+        original_image
+    ], queue = False, show_progress = False).then(check, inputs = [
+        source_img,
+        prompt,
+        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(redraw, inputs = [
+        source_img,
+        prompt,
+        negative_prompt,
+        num_inference_steps,
+        guidance_scale,
+        image_guidance_scale,
+        strength,
+        denoising_steps,
+        randomize_seed,
+        seed,
+        debug_mode
+    ], outputs = [
+        redrawn_image,
+        information,
+        original_image
+    ], scroll_to_output = True)
+
+    gr.Examples(
+        run_on_click = True,
+        fn = redraw,
+	    inputs = [
+            source_img,
+            prompt,
+            negative_prompt,
+            num_inference_steps,
+            guidance_scale,
+            image_guidance_scale,
+            strength,
+            denoising_steps,
+            randomize_seed,
+            seed,
+            debug_mode
+        ],
+	    outputs = [
+            redrawn_image,
+            information,
+            original_image
+        ],
+        examples = [
+                [
+                    "./Examples/Example1.png",
+                    "Drawn image, line art, illustration, picture",
+                    "3d, photo, realistic, noise, blur, watermark",
+                    25,
+                    7,
+                    1.1,
+                    0.6,
+                    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
+        ```
+        """
+    )
+
+    interface.queue().launch()