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
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")
#device = "cuda" if torch.cuda.is_available() else "cpu"
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print("The model will be running on :: ", device, " ~device")
pipe = StableDiffusionInpaintingPipeline.from_pretrained(
"CompVis/stable-diffusion-v1-4",
#revision="fp16",
torch_dtype=torch.float16,
use_auth_token=auth_token,
).to(device)
#model = CLIPDensePredT(version='ViT-B/16', reduce_dim=64)
model = CLIPDensePredT(version='ViT-B/16', reduce_dim=64, complex_trans_conv=True)
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))
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"):
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}
'''
def swap_word_mask(radio_option):
if(radio_option == "type what to mask below"):
return gr.update(interactive=True, placeholder="A cat")
else:
return gr.update(interactive=False, placeholder="Disabled")
image_blocks = gr.Blocks(css=css)
with image_blocks as demo:
gr.HTML(
"""
Stable Diffusion Multi Inpainting
Inpaint Stable Diffusion by either drawing a mask or typing what to replace
"""
)
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(
"""
LICENSE
The model is licensed with a CreativeML Open RAIL-M 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 read the license
Biases and content acknowledgment
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 LAION-5B dataset, 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 model card