Spaces:
Runtime error
Runtime error
File size: 6,031 Bytes
8dcc2d5 b7133f4 6b27ec4 b7133f4 8dcc2d5 b7133f4 6ed0225 b7133f4 6ed0225 b7133f4 1ff2b57 b7133f4 8dcc2d5 b7133f4 6ed0225 b7133f4 6ed0225 b7133f4 6ed0225 b7133f4 6ed0225 1ff2b57 6ed0225 1ff2b57 6ed0225 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 |
import gradio as gr
from io import BytesIO
import requests
import PIL
from PIL import Image
import numpy as np
import os
import uuid
import torch
from torch import autocast
import cv2
from matplotlib import pyplot as plt
from inpainting import StableDiffusionInpaintingPipeline
from torchvision import transforms
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")
device = "cuda" if torch.cuda.is_available() else "cpu"
pipe = StableDiffusionInpaintingPipeline.from_pretrained(
"CompVis/stable-diffusion-v1-4",
revision="fp16",
torch_dtype=torch.float16,
use_auth_token=auth_token,
).to(device)
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(dict, prompt=""):
with autocast("cuda"):
init_image = dict["image"].convert("RGB").resize((512, 512))
mask = dict["mask"].convert("RGB").resize((512, 512))
images = pipe(prompt = prompt, init_image=init_image, mask_image=mask, strength=0.8)["sample"]
return 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}
'''
image_blocks = gr.Blocks(css=css)
with image_blocks as demo:
gr.HTML(
"""
<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;
"
>
<h1 style="font-weight: 900; margin-bottom: 7px;">
Stable Diffusion Inpainting
</h1>
</div>
<p style="margin-bottom: 10px; font-size: 94%">
Stable Diffusion Inpainting by RunwayML, add a mask and text prompt for what you want to replace <br>For faster generation you can try
<a
href="https://app.runwayml.com/video-tools/teams/akhaliq/ai-tools/erase-and-replace"
style="text-decoration: underline;"
target="_blank"
>erase and replace tool on Runway</a
>
</p>
</div>
"""
)
with gr.Group():
with gr.Box():
image = gr.Image(source='upload', tool='sketch', elem_id="image_upload", type="pil", label="Upload").style(height=400)
with gr.Row(elem_id="prompt-container").style(mobile_collapse=False, equal_height=True):
prompt = gr.Textbox(label = 'Your prompt (what you want to replace)')
btn = gr.Button("Generate image").style(
margin=False,
rounded=(False, True, True, False),
full_width=False,
)
ex = gr.Examples(fn=predict, inputs=[image, prompt], outputs=image, cache_examples=False)
ex.dataset.headers = [""]
btn.click(fn=predict, inputs=[image, prompt], outputs=image)
gr.HTML(
"""
<div class="footer">
<p>Model by <a href="https://huggingface.co/runwayml" style="text-decoration: underline;" target="_blank">RunwayML</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>
"""
)
image_blocks.launch() |