Upload 3 files

README.md

@@ -1,13 +1,23 @@
 ---
-title: Stable Diffusion Inpainting
-emoji: ⚡
-colorFrom: gray
-colorTo: yellow
+title: Inpaint SDXL (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: 3.11.0
+sdk_version: 3.41.2
 app_file: app.py
 pinned: false
 license: mit
+short_description: Modifies one detail of your image, at any resolution, freely
 ---
 
-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

@@ -1,174 +1,351 @@
+from diffusers import StableDiffusionXLInpaintPipeline
+from PIL import Image, ImageFilter
+
 import gradio as gr
-#test
-from io import BytesIO
-import requests
-import PIL
-from PIL import Image
 import numpy as np
-import os
-import uuid
+import time
+import math
+import random
+import imageio
 import torch
-from torch import autocast
-import cv2
-from matplotlib import pyplot as plt
-from diffusers import DiffusionPipeline
-from torchvision import transforms
-from clipseg.models.clipseg import CLIPDensePredT
-
-auth_token = os.environ.get("API_TOKEN") or True
 
-def download_image(url):
-    response = requests.get(url)
-    return PIL.Image.open(BytesIO(response.content)).convert("RGB")
+max_64_bit_int = 2**63 - 1
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
-pipe = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-inpainting",
-    revision="fp16", 
-    torch_dtype=torch.float16,
-    use_auth_token=auth_token,
-).to(device)
-
-model = CLIPDensePredT(version='ViT-B/16', reduce_dim=64)
-model.eval()
-model.load_state_dict(torch.load('./clipseg/weights/rd64-uni.pth', map_location=torch.device('cuda')), strict=False)
-
-transform = transforms.Compose([
-      transforms.ToTensor(),
-      transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      transforms.Resize((512, 512)),
-])
-
-def predict(radio, dict, word_mask, prompt=""):
-    if(radio == "draw a mask above"):
-        with autocast("cuda"):
-            init_image = dict["image"].convert("RGB").resize((512, 512))
-            mask = dict["mask"].convert("RGB").resize((512, 512))
+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:
-        img = transform(dict["image"]).unsqueeze(0)
-        word_masks = [word_mask]
-        with torch.no_grad():
-            preds = model(img.repeat(len(word_masks),1,1,1), word_masks)[0]
-        init_image = dict['image'].convert('RGB').resize((512, 512))
-        filename = f"{uuid.uuid4()}.png"
-        plt.imsave(filename,torch.sigmoid(preds[0][0]))
-        img2 = cv2.imread(filename)
-        gray_image = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)
-        (thresh, bw_image) = cv2.threshold(gray_image, 100, 255, cv2.THRESH_BINARY)
-        cv2.cvtColor(bw_image, cv2.COLOR_BGR2RGB)
-        mask = Image.fromarray(np.uint8(bw_image)).convert('RGB')
-        os.remove(filename)
-    #with autocast("cuda"):
-    output = pipe(prompt = prompt, image=init_image, mask_image=mask, strength=0.8)
-    return output.images[0]
-
-# examples = [[dict(image="init_image.png", mask="mask_image.png"), "A panda sitting on a bench"]]
-css = '''
-.container {max-width: 1150px;margin: auto;padding-top: 1.5rem}
-#image_upload{min-height:400px}
-#image_upload [data-testid="image"], #image_upload [data-testid="image"] > div{min-height: 400px}
-#mask_radio .gr-form{background:transparent; border: none}
-#word_mask{margin-top: .75em !important}
-#word_mask textarea:disabled{opacity: 0.3}
-.footer {margin-bottom: 45px;margin-top: 35px;text-align: center;border-bottom: 1px solid #e5e5e5}
-.footer>p {font-size: .8rem; display: inline-block; padding: 0 10px;transform: translateY(10px);background: white}
-.dark .footer {border-color: #303030}
-.dark .footer>p {background: #0b0f19}
-.acknowledgments h4{margin: 1.25em 0 .25em 0;font-weight: bold;font-size: 115%}
-#image_upload .touch-none{display: flex}
-'''
-def swap_word_mask(radio_option):
-    if(radio_option == "type what to mask below"):
-        return gr.update(interactive=True, placeholder="A cat")
+        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:
-        return gr.update(interactive=False, placeholder="Disabled")
+        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]
 
-image_blocks = gr.Blocks(css=css)
-with image_blocks as demo:
-    gr.HTML(
+    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(
         """
-            <div style="text-align: center; max-width: 650px; margin: 0 auto;">
-              <div
-                style="
-                  display: inline-flex;
-                  align-items: center;
-                  gap: 0.8rem;
-                  font-size: 1.75rem;
-                "
-              >
-                <svg
-                  width="0.65em"
-                  height="0.65em"
-                  viewBox="0 0 115 115"
-                  fill="none"
-                  xmlns="http://www.w3.org/2000/svg"
-                >
-                  <rect width="23" height="23" fill="white"></rect>
-                  <rect y="69" width="23" height="23" fill="white"></rect>
-                  <rect x="23" width="23" height="23" fill="#AEAEAE"></rect>
-                  <rect x="23" y="69" width="23" height="23" fill="#AEAEAE"></rect>
-                  <rect x="46" width="23" height="23" fill="white"></rect>
-                  <rect x="46" y="69" width="23" height="23" fill="white"></rect>
-                  <rect x="69" width="23" height="23" fill="black"></rect>
-                  <rect x="69" y="69" width="23" height="23" fill="black"></rect>
-                  <rect x="92" width="23" height="23" fill="#D9D9D9"></rect>
-                  <rect x="92" y="69" width="23" height="23" fill="#AEAEAE"></rect>
-                  <rect x="115" y="46" width="23" height="23" fill="white"></rect>
-                  <rect x="115" y="115" width="23" height="23" fill="white"></rect>
-                  <rect x="115" y="69" width="23" height="23" fill="#D9D9D9"></rect>
-                  <rect x="92" y="46" width="23" height="23" fill="#AEAEAE"></rect>
-                  <rect x="92" y="115" width="23" height="23" fill="#AEAEAE"></rect>
-                  <rect x="92" y="69" width="23" height="23" fill="white"></rect>
-                  <rect x="69" y="46" width="23" height="23" fill="white"></rect>
-                  <rect x="69" y="115" width="23" height="23" fill="white"></rect>
-                  <rect x="69" y="69" width="23" height="23" fill="#D9D9D9"></rect>
-                  <rect x="46" y="46" width="23" height="23" fill="black"></rect>
-                  <rect x="46" y="115" width="23" height="23" fill="black"></rect>
-                  <rect x="46" y="69" width="23" height="23" fill="black"></rect>
-                  <rect x="23" y="46" width="23" height="23" fill="#D9D9D9"></rect>
-                  <rect x="23" y="115" width="23" height="23" fill="#AEAEAE"></rect>
-                  <rect x="23" y="69" width="23" height="23" fill="black"></rect>
-                </svg>
-                <h1 style="font-weight: 900; margin-bottom: 7px;">
-                  Stable Diffusion Multi Inpainting
-                </h1>
-              </div>
-              <p style="margin-bottom: 10px; font-size: 94%">
-                Inpaint Stable Diffusion by either drawing a mask or typing what to replace
-              </p>
-            </div>
+        <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.
+        <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/multimodalart/stable-diffusion-inpainting?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.Row():
-        with gr.Column():
-            image = gr.Image(source='upload', tool='sketch', elem_id="image_upload", type="pil", label="Upload").style(height=400)
-            with gr.Box(elem_id="mask_radio").style(border=False):
-                radio = gr.Radio(["draw a mask above", "type what to mask below"], value="draw a mask above", show_label=False, interactive=True).style(container=False)
-                word_mask = gr.Textbox(label = "What to find in your image", interactive=False, elem_id="word_mask", placeholder="Disabled").style(container=False)
-            prompt = gr.Textbox(label = 'Your prompt (what you want to add in place of what you are removing)')
-            radio.change(fn=swap_word_mask, inputs=radio, outputs=word_mask,show_progress=False)
-            radio.change(None, inputs=[], outputs=image_blocks, _js = """
-            () => {
-                css_style = document.styleSheets[document.styleSheets.length - 1]
-                last_item = css_style.cssRules[css_style.cssRules.length - 1]
-                last_item.style.display = ["flex", ""].includes(last_item.style.display) ? "none" : "flex";
-            }""")
-            btn = gr.Button("Run")
-        with gr.Column():
-            result = gr.Image(label="Result")
-        btn.click(fn=predict, inputs=[radio, image, word_mask, prompt], outputs=result)
-    gr.HTML(
-            """
-                <div class="footer">
-                    <p>Model by <a href="https://huggingface.co/CompVis" style="text-decoration: underline;" target="_blank">CompVis</a> and <a href="https://huggingface.co/stabilityai" style="text-decoration: underline;" target="_blank">Stability AI</a> - Inpainting by <a href="https://github.com/nagolinc" style="text-decoration: underline;" target="_blank">nagolinc</a> and <a href="https://github.com/patil-suraj" style="text-decoration: underline;">patil-suraj</a>, inpainting with words by <a href="https://twitter.com/yvrjsharma/" style="text-decoration: underline;" target="_blank">@yvrjsharma</a> and <a href="https://twitter.com/1littlecoder" style="text-decoration: underline;">@1littlecoder</a> - Gradio Demo by 🤗 Hugging Face
-                    </p>
-                </div>
-                <div class="acknowledgments">
-                    <p><h4>LICENSE</h4>
-The model is licensed with a <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" style="text-decoration: underline;" target="_blank">CreativeML Open RAIL-M</a> license. The authors claim no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in this license. The license forbids you from sharing any content that violates any laws, produce any harm to a person, disseminate any personal information that would be meant for harm, spread misinformation and target vulnerable groups. For the full list of restrictions please <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" target="_blank" style="text-decoration: underline;" target="_blank">read the license</a></p>
-                    <p><h4>Biases and content acknowledgment</h4>
-Despite how impressive being able to turn text into image is, beware to the fact that this model may output content that reinforces or exacerbates societal biases, as well as realistic faces, pornography and violence. The model was trained on the <a href="https://laion.ai/blog/laion-5b/" style="text-decoration: underline;" target="_blank">LAION-5B dataset</a>, which scraped non-curated image-text-pairs from the internet (the exception being the removal of illegal content) and is meant for research purposes. You can read more in the <a href="https://huggingface.co/CompVis/stable-diffusion-v1-4" style="text-decoration: underline;" target="_blank">model card</a></p>
-               </div>
-           """
-        )
-demo.launch()
+    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/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
+                ],
+                [
+                    "./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
+                ],
+            ],
+        cache_examples = False,
+    )
+
+    interface.queue().launch()

requirements.txt

@@ -1,11 +1,8 @@
---extra-index-url https://download.pytorch.org/whl/cu113 
-torch
 torchvision
-diffusers==0.6.0
-transformers==4.23.1
+diffusers
+transformers
+accelerate
 ftfy
-numpy
-matplotlib
-uuid
-opencv-python
-git+https://github.com/openai/CLIP.git
+scipy
+imageio
+invisible_watermark