Upload the app

README.md

@@ -1,12 +1,22 @@
 ---
-title: Inpaint Prod
-emoji: 🏆
-colorFrom: gray
-colorTo: gray
+title: SDXL inpaint (any size)
+emoji: ↔️
+colorFrom: blue
+colorTo: purple
+tags:
+- Image-to-Image
+- Image-2-Image
+- Img-to-Img
+- Img-2-Img
+- SDXL
+- Stable Diffusion
+- language models
+- LLMs
 sdk: gradio
-sdk_version: 4.20.0
+sdk_version: 3.41.2
 app_file: app.py
 pinned: false
+license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,361 @@
+from diffusers import StableDiffusionXLInpaintPipeline
+from PIL import Image, ImageFilter
+
+import gradio as gr
+import numpy as np
+import time
+import math
+import random
+import imageio
+import torch
+
+max_64_bit_int = 2**63 - 1
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+floatType = torch.float16 if torch.cuda.is_available() else torch.float32
+variant = "fp16" if torch.cuda.is_available() else None
+pipe = StableDiffusionXLInpaintPipeline.from_pretrained("diffusers/stable-diffusion-xl-1.0-inpainting-0.1", torch_dtype = floatType, variant = variant)
+pipe = pipe.to(device)
+
+def check(
+    source_img,
+    prompt,
+    uploaded_mask,
+    negative_prompt,
+    denoising_steps,
+    num_inference_steps,
+    guidance_scale,
+    image_guidance_scale,
+    strength,
+    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,
+    negative_prompt,
+    denoising_steps,
+    num_inference_steps,
+    guidance_scale,
+    image_guidance_scale,
+    strength,
+    randomize_seed,
+    seed,
+    debug_mode,
+    progress = gr.Progress()
+):
+    check(
+        source_img,
+        prompt,
+        uploaded_mask,
+        negative_prompt,
+        denoising_steps,
+        num_inference_steps,
+        guidance_scale,
+        image_guidance_scale,
+        strength,
+        randomize_seed,
+        seed,
+        debug_mode
+    )
+    start = time.time()
+    progress(0, desc = "Preparing data...")
+
+    if negative_prompt is None:
+        negative_prompt = ""
+
+    if denoising_steps is None:
+        denoising_steps = 1000
+
+    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 randomize_seed:
+        seed = random.randint(0, max_64_bit_int)
+
+    random.seed(seed)
+    #pipe = pipe.manual_seed(seed)
+
+    input_image = source_img["image"].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["mask"].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)
+
+    progress(None, desc = "Processing...")
+    output_image = 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]
+
+    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 = 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,
+        input_image,
+        mask_image
+    ]
+
+def toggle_debug(is_debug_mode):
+    if is_debug_mode:
+        return [gr.update(visible = True)] * 2
+    else:
+        return [gr.update(visible = False)] * 2
+
+with gr.Blocks() as interface:
+    gr.Markdown(
+        """
+        <p style="text-align: center;"><b><big><big><big>Inpaint</big></big></big></b></p>
+        <p style="text-align: center;">Modifies one detail of your image, at any resolution, freely, without account, without watermark, without installation, which can be downloaded</p>
+        <br/>
+        <br/>
+        🚀 Powered by <i>SDXL 1.0</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>Ilaria Upscaler</i>,</li>
+        <li>To <b>slightly change</b> your image, I recommend to use <i>Image-to-Image 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... ~1 hour.<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/Inpaint?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", source = "upload", tool = "sketch", 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 in the entire image")
+        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)", source = "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")
+             denoising_steps = gr.Slider(minimum = 0, maximum = 1000, value = 1000, step = 1, label = "Denoising", info = "lower=irrelevant result, higher=relevant result")
+             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")
+             strength = gr.Number(value = 0.99, minimum = 0.01, maximum = 1.0, step = 0.01, label = "Strength", info = "lower=follow the original area, higher=redraw from scratch")
+             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)")
+             debug_mode = gr.Checkbox(label = "Debug mode", value = False, info = "Show intermediate results")
+
+        submit = gr.Button("Inpaint", variant = "primary")
+
+        inpainted_image = gr.Image(label = "Inpainted image")
+        information = gr.Label(label = "Information")
+        original_image = gr.Image(label = "Original image", visible = False)
+        mask_image = gr.Image(label = "Mask image", visible = False)
+
+    submit.click(toggle_debug, debug_mode, [
+        original_image,
+        mask_image
+    ], queue = False, show_progress = False).then(check, inputs = [
+        source_img,
+        prompt,
+        uploaded_mask,
+        negative_prompt,
+        denoising_steps,
+        num_inference_steps,
+        guidance_scale,
+        image_guidance_scale,
+        strength,
+        randomize_seed,
+        seed,
+        debug_mode
+    ], outputs = [], queue = False, show_progress = False).success(inpaint, inputs = [
+        source_img,
+        prompt,
+        uploaded_mask,
+        negative_prompt,
+        denoising_steps,
+        num_inference_steps,
+        guidance_scale,
+        image_guidance_scale,
+        strength,
+        randomize_seed,
+        seed,
+        debug_mode
+    ], outputs = [
+        inpainted_image,
+        information,
+        original_image,
+        mask_image
+    ], scroll_to_output = True)
+
+    gr.Examples(
+	    inputs = [
+            source_img,
+            prompt,
+            uploaded_mask,
+            negative_prompt,
+            denoising_steps,
+            num_inference_steps,
+            guidance_scale,
+            image_guidance_scale,
+            strength,
+            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",
+                    "Painting, drawing, cartoon, ugly, malformed, noise, blur, watermark",
+                    1000,
+                    25,
+                    7,
+                    1.1,
+                    0.99,
+                    True,
+                    42,
+                    False
+                ],
+                [
+                    "./Examples/Example2.webp",
+                    "A cat, ultrarealistic, realistic, photorealistic, 8k",
+                    "./Examples/Mask2.png",
+                    "Painting, drawing, cartoon, ugly, malformed, noise, blur, watermark",
+                    1000,
+                    25,
+                    7,
+                    1.1,
+                    0.99,
+                    True,
+                    42,
+                    False
+                ],
+                [
+                    "./Examples/Example3.jpg",
+                    "An angry old woman, ultrarealistic, realistic, photorealistic, 8k",
+                    "./Examples/Mask3.gif",
+                    "Painting, drawing, cartoon, ugly, malformed, noise, blur, watermark",
+                    1000,
+                    25,
+                    7,
+                    1.5,
+                    0.99,
+                    True,
+                    42,
+                    False
+                ],
+                [
+                    "./Examples/Example4.gif",
+                    "A laptop, ultrarealistic, realistic, photorealistic, 8k",
+                    "./Examples/Mask4.bmp",
+                    "Painting, drawing, cartoon, ugly, malformed, noise, blur, watermark",
+                    1000,
+                    25,
+                    7,
+                    1.1,
+                    0.99,
+                    True,
+                    42,
+                    False
+                ],
+                [
+                    "./Examples/Example5.bmp",
+                    "A sand castle, ultrarealistic, realistic, photorealistic, 8k",
+                    "./Examples/Mask5.png",
+                    "Painting, drawing, cartoon, ugly, malformed, noise, blur, watermark",
+                    1000,
+                    50,
+                    7,
+                    1.5,
+                    0.5,
+                    True,
+                    42,
+                    False
+                ],
+            ],
+        cache_examples = False,
+    )
+
+    interface.queue().launch()

requirements.txt

@@ -0,0 +1,8 @@
+torchvision
+diffusers
+transformers
+accelerate
+ftfy
+scipy
+imageio
+invisible_watermark