HD-Painter / app.py
Andranik Sargsyan
fix examples
fd3e2fa
raw
history blame
13.7 kB
import os
from collections import OrderedDict
import gradio as gr
import shutil
import uuid
import torch
from pathlib import Path
from lib.utils.iimage import IImage
from PIL import Image
from lib import models
from lib.methods import rasg, sd, sr
from lib.utils import poisson_blend, image_from_url_text
TMP_DIR = 'gradio_tmp'
if Path(TMP_DIR).exists():
shutil.rmtree(TMP_DIR)
Path(TMP_DIR).mkdir(exist_ok=True, parents=True)
os.environ['GRADIO_TEMP_DIR'] = TMP_DIR
on_huggingspace = os.environ.get("SPACE_AUTHOR_NAME") == "PAIR"
negative_prompt_str = "text, bad anatomy, bad proportions, blurry, cropped, deformed, disfigured, duplicate, error, extra limbs, gross proportions, jpeg artifacts, long neck, low quality, lowres, malformed, morbid, mutated, mutilated, out of frame, ugly, worst quality"
positive_prompt_str = "Full HD, 4K, high quality, high resolution"
example_inputs = [
['assets/examples/images/a40.jpg', 'medieval castle'],
['assets/examples/images/a4.jpg', 'parrot'],
['assets/examples/images/a65.jpg', 'hoodie'],
['assets/examples/images/a54.jpg', 'salad'],
['assets/examples/images/a51.jpg', 'space helmet'],
['assets/examples/images/a46.jpg', 'stack of books'],
['assets/examples/images/a19.jpg', 'antique greek vase'],
['assets/examples/images/a2.jpg', 'sunglasses'],
]
thumbnails = [
'https://lh3.googleusercontent.com/pw/ABLVV87bkFc_SRKrbXuk5BTp18dETNm18MLbjoJo6JvwbIkYtjZXrjU_H1dCJIP799OJjHTZmo19mYVyMCC1RLmwqzoZrgwQzfB-SCtxLa83IbXBQ23xzmKoZgsRlPztxNJD6gmXzFyatdLRzDxHIusBQLUz=w3580-h1150-s-no-gm',
'https://lh3.googleusercontent.com/pw/ABLVV85RWtrpTf1tMp2p3q37eg5DlFp5znifALK_JTjvxJua8UYMjytVoEy2GUW2cLXgBvQyYKg7GvrWXQ5hkdAsyih5Rf4rFnDq-JoiQYhVZHStCZLKxmeAlQna5ZwMPVTKG1TK63DH_OdK58gvSjWtF2ww=w3580-h1152-s-no-gm',
'https://lh3.googleusercontent.com/pw/ABLVV84dkaU6SQs9fyDjajpk1X9JkYp_zQBEnPVL67oi11_05U6-Ys5ydQpuny8GBQCMyVbFKxJ5unn9w__gmP9K0cKQ4_IVoT7Hvfmya71klDqSI7vu9Iy_5P2Il5-0giJFpumtffBA3kryn1xtJdR4vSA0=w2924-h1858-s-no-gm',
'https://lh3.googleusercontent.com/pw/ABLVV853ZyjvS4LvcPpVMY9BWz-232omt3-hgRiGcky_3ojE6WLKgtsrftsg1jSrUm2ccT_UOa279CulZy6fdnH_Xg1SunyRBxaRjOK0uxAkUFwb60rR1S4hI2MmhLV7KCi3tw1A-oiGi0f9JINyade-322A=w2622-h1858-s-no-gm',
'https://lh3.googleusercontent.com/pw/ABLVV86AJGUVGjb0i6CPg8zlJlWObNY0xdOzM1x5Bq9gKhP-ZWre5aaexRJDxQUO2gmJtRIyohD88FJDG_aVX2G5M0QOyGRWlZmx7tOVXLh-Kbesobxo9MfD-wqk9Ts9O8NUGtIwkWzo9SEs2opKdu83gB9F=w2528-h1858-s-no-gm',
'https://lh3.googleusercontent.com/pw/ABLVV87MplTciS7z-4i-eY3B3L0YhaK8UEQ3pTQD6W6uYVGR4hPD9u1WGEGyfg5ddqU-Bx2BrKskDhwxzF746cRhgFU5aPtbYA_-O7KfqXe9IsMxYCgUKxEHBm2ncqy64V-w-N8XOFgUMkAQqcuuNZ8Xapqp=w3580-h1186-s-no-gm',
'https://lh3.googleusercontent.com/pw/ABLVV877Esi6l2Kuw3akH5QBlmDAbWydZDZEEJqlZ_N-X7g33NQZU8nv_UKdAVETS7q23byTuldIAhW-q99zCycFB8Yfc-5e_WPNIM9icU0p3gd6DUVZR233ZNUtLca384MYGIhMGud9Y_Xed1I3PpiMhrpG=w2846-h1858-s-no-gm',
'https://lh3.googleusercontent.com/pw/ABLVV85hMQbSB6fCokdyut4ke7xTUqjERhuYygnj7T8IIA1k48e9GkaowDywPZzi5QJzZfj7wU3bgBHzjxop19qK1zOi5XDrjfXkn5bwj4MxicHa3TG-Rc-V-c1uyZVUyviyUlkGZ62FxuVROw2x0aGJIcr0=w3580-h1382-s-no-gm'
]
example_previews = [
[thumbnails[0], 'Prompt: medieval castle'],
[thumbnails[1], 'Prompt: parrot'],
[thumbnails[2], 'Prompt: hoodie'],
[thumbnails[3], 'Prompt: salad'],
[thumbnails[4], 'Prompt: space helmet'],
[thumbnails[5], 'Prompt: laptop'],
[thumbnails[6], 'Prompt: antique greek vase'],
[thumbnails[7], 'Prompt: sunglasses'],
]
# Load models
inpainting_models = OrderedDict([
("Dreamshaper Inpainting V8", models.ds_inp.load_model()),
("Stable-Inpainting 2.0", models.sd2_inp.load_model()),
("Stable-Inpainting 1.5", models.sd15_inp.load_model())
])
sr_model = models.sd2_sr.load_model(device='cuda:1')
sam_predictor = models.sam.load_model(device='cuda:0')
inp_model = inpainting_models[list(inpainting_models.keys())[0]]
def set_model_from_name(inp_model_name):
global inp_model
print (f"Activating Inpaintng Model: {inp_model_name}")
inp_model = inpainting_models[inp_model_name]
def rasg_run(
use_painta, prompt, input, seed, eta,
negative_prompt, positive_prompt, ddim_steps,
guidance_scale=7.5,
batch_size=1
):
torch.cuda.empty_cache()
seed = int(seed)
batch_size = max(1, min(int(batch_size), 4))
image = IImage(input['image']).resize(512)
mask = IImage(input['mask']).rgb().resize(512)
method = ['rasg']
if use_painta: method.append('painta')
method = '-'.join(method)
inpainted_images = []
blended_images = []
for i in range(batch_size):
seed = seed + i * 1000
inpainted_image = rasg.run(
ddim=inp_model,
method=method,
prompt=prompt,
image=image,
mask=mask,
seed=seed,
eta=eta,
negative_prompt=negative_prompt,
positive_prompt=positive_prompt,
num_steps=ddim_steps,
guidance_scale=guidance_scale
).crop(image.size)
blended_image = poisson_blend(
orig_img=image.data[0],
fake_img=inpainted_image.data[0],
mask=mask.data[0],
dilation=12
)
blended_images.append(blended_image)
inpainted_images.append(inpainted_image.numpy()[0])
return blended_images, inpainted_images
def sd_run(use_painta, prompt, input, seed, eta,
negative_prompt, positive_prompt, ddim_steps,
guidance_scale=7.5,
batch_size=1
):
torch.cuda.empty_cache()
seed = int(seed)
batch_size = max(1, min(int(batch_size), 4))
image = IImage(input['image']).resize(512)
mask = IImage(input['mask']).rgb().resize(512)
method = ['default']
if use_painta: method.append('painta')
method = '-'.join(method)
inpainted_images = []
blended_images = []
for i in range(batch_size):
seed = seed + i * 1000
inpainted_image = sd.run(
ddim=inp_model,
method=method,
prompt=prompt,
image=image,
mask=mask,
seed=seed,
eta=eta,
negative_prompt=negative_prompt,
positive_prompt=positive_prompt,
num_steps=ddim_steps,
guidance_scale=guidance_scale
).crop(image.size)
blended_image = poisson_blend(
orig_img=image.data[0],
fake_img=inpainted_image.data[0],
mask=mask.data[0],
dilation=12
)
blended_images.append(blended_image)
inpainted_images.append(inpainted_image.numpy()[0])
return blended_images, inpainted_images
def upscale_run(
prompt, input, ddim_steps, seed, use_sam_mask, gallery, img_index,
negative_prompt='',
positive_prompt=', high resolution professional photo'
):
torch.cuda.empty_cache()
seed = int(seed)
img_index = int(img_index)
img_index = 0 if img_index < 0 else img_index
img_index = len(gallery) - 1 if img_index >= len(gallery) else img_index
img_info = gallery[img_index if img_index >= 0 else 0]
inpainted_image = image_from_url_text(img_info)
lr_image = IImage(inpainted_image)
hr_image = IImage(input['image']).resize(2048)
hr_mask = IImage(input['mask']).resize(2048)
output_image = sr.run(
sr_model,
sam_predictor,
lr_image,
hr_image,
hr_mask,
prompt=prompt + positive_prompt,
noise_level=20,
blend_trick=True,
blend_output=True,
negative_prompt=negative_prompt,
seed=seed,
use_sam_mask=use_sam_mask
)
output_image.info = input['image'].info # save metadata
return output_image, output_image
def switch_run(use_rasg, model_name, *args):
set_model_from_name(model_name)
if use_rasg:
return rasg_run(*args)
return sd_run(*args)
with gr.Blocks(css='style.css') as demo:
gr.HTML(
"""
<div style="text-align: center; max-width: 1200px; margin: 20px auto;">
<h1 style="font-weight: 900; font-size: 3rem; margin-bottom: 0.5rem">
πŸ§‘β€πŸŽ¨ HD-Painter Demo
</h1>
<h2 style="font-weight: 450; font-size: 1rem; margin: 0rem">
Hayk Manukyan<sup>1*</sup>, Andranik Sargsyan<sup>1*</sup>, Barsegh Atanyan<sup>1</sup>, Zhangyang Wang<sup>1,2</sup>, Shant Navasardyan<sup>1</sup>
and <a href="https://www.humphreyshi.com/home">Humphrey Shi</a><sup>1,3</sup>
</h2>
<h2 style="font-weight: 450; font-size: 1rem; margin: 0rem">
<sup>1</sup>Picsart AI Resarch (PAIR), <sup>2</sup>UT Austin, <sup>3</sup>Georgia Tech
</h2>
<h2 style="font-weight: 450; font-size: 1rem; margin: 0rem">
[<a href="https://arxiv.org/abs/2312.14091" style="color:blue;">arXiv</a>]
[<a href="https://github.com/Picsart-AI-Research/HD-Painter" style="color:blue;">GitHub</a>]
</h2>
<h2 style="font-weight: 450; font-size: 1rem; margin: 0.7rem auto; max-width: 1000px">
<b>HD-Painter</b> enables prompt-faithfull and high resolution (up to 2k) image inpainting upon any diffusion-based image inpainting method.
</h2>
</div>
""")
if on_huggingspace:
gr.HTML("""
<p>For faster inference without waiting in queue, you may duplicate the space and upgrade to the suggested GPU in settings.
<br/>
<a href="https://huggingface.co/spaces/PAIR/HD-Painter?duplicate=true">
<img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
</p>""")
with open('script.js', 'r') as f:
js_str = f.read()
demo.load(_js=js_str)
with gr.Row():
with gr.Column():
model_picker = gr.Dropdown(
list(inpainting_models.keys()),
value=list(inpainting_models.keys())[0],
label = "Please select a model!",
)
with gr.Column():
use_painta = gr.Checkbox(value = True, label = "Use PAIntA")
use_rasg = gr.Checkbox(value = True, label = "Use RASG")
prompt = gr.Textbox(label = "Inpainting Prompt")
with gr.Row():
with gr.Column():
input = gr.ImageMask(label = "Input Image", brush_color='#ff0000', elem_id="inputmask", type="pil")
with gr.Row():
inpaint_btn = gr.Button("Inpaint", scale = 0)
with gr.Accordion('Advanced options', open=False):
guidance_scale = gr.Slider(minimum = 0, maximum = 30, value = 7.5, label = "Guidance Scale")
eta = gr.Slider(minimum = 0, maximum = 1, value = 0.1, label = "eta")
ddim_steps = gr.Slider(minimum = 10, maximum = 100, value = 50, step = 1, label = 'Number of diffusion steps')
with gr.Row():
seed = gr.Number(value = 49123, label = "Seed")
batch_size = gr.Number(value = 1, label = "Batch size", minimum=1, maximum=4)
negative_prompt = gr.Textbox(value=negative_prompt_str, label = "Negative prompt", lines=3)
positive_prompt = gr.Textbox(value=positive_prompt_str, label = "Positive prompt", lines=1)
with gr.Column():
with gr.Row():
output_gallery = gr.Gallery(
[],
columns = 4,
preview = True,
allow_preview = True,
object_fit='scale-down',
elem_id='outputgallery'
)
with gr.Row():
upscale_btn = gr.Button("Send to Inpainting-Specialized Super-Resolution (x4)", scale = 1)
with gr.Row():
use_sam_mask = gr.Checkbox(value = False, label = "Use SAM mask for background preservation (for SR only, experimental feature)")
with gr.Row():
hires_image = gr.Image(label = "Hi-res Image")
label = gr.Markdown("## High-Resolution Generation Samples (2048px large side)")
with gr.Column():
example_container = gr.Gallery(
example_previews,
columns = 4,
preview = True,
allow_preview = True,
object_fit='scale-down'
)
gr.Examples(
[
example_inputs[i] + [[example_previews[i]]]
for i in range(len(example_previews))
],
[input, prompt, example_container]
)
mock_output_gallery = gr.Gallery([], columns = 4, visible=False)
mock_hires = gr.Image(label = "__MHRO__", visible = False)
html_info = gr.HTML(elem_id=f'html_info', elem_classes="infotext")
inpaint_btn.click(
fn=switch_run,
inputs=[
use_rasg,
model_picker,
use_painta,
prompt,
input,
seed,
eta,
negative_prompt,
positive_prompt,
ddim_steps,
guidance_scale,
batch_size
],
outputs=[output_gallery, mock_output_gallery],
api_name="inpaint"
)
upscale_btn.click(
fn=upscale_run,
inputs=[
prompt,
input,
ddim_steps,
seed,
use_sam_mask,
mock_output_gallery,
html_info
],
outputs=[hires_image, mock_hires],
api_name="upscale",
_js="function(a, b, c, d, e, f, g){ return [a, b, c, d, e, f, selected_gallery_index()] }",
)
demo.queue(max_size=20)
demo.launch(share=True, allowed_paths=[TMP_DIR])