GT_VTR3_1 / run /gradio_ootd copy_backup.py
Ubuntu
improved inference time
3bc69b8
import gradio as gr
import os
from pathlib import Path
import sys
import torch
from PIL import Image, ImageOps
import numpy as np
from utils_ootd import get_mask_location
PROJECT_ROOT = Path(__file__).absolute().parents[1].absolute()
sys.path.insert(0, str(PROJECT_ROOT))
from preprocess.openpose.run_openpose import OpenPose
from preprocess.humanparsing.run_parsing import Parsing
from ootd.inference_ootd_hd import OOTDiffusionHD
from ootd.inference_ootd_dc import OOTDiffusionDC
from preprocess.openpose.annotator.openpose.util import draw_bodypose
# Set default dtype to float64
# torch.set_default_dtype(torch.float16)
openpose_model_hd = OpenPose(0)
parsing_model_hd = Parsing(0)
ootd_model_hd = OOTDiffusionHD(0)
openpose_model_dc = OpenPose(0)
parsing_model_dc = Parsing(0)
ootd_model_dc = OOTDiffusionDC(0)
category_dict = ['upperbody', 'lowerbody', 'dress']
category_dict_utils = ['upper_body', 'lower_body', 'dresses']
example_path = os.path.join(os.path.dirname(__file__), 'examples')
model_hd = os.path.join(example_path, 'model/model_1.png')
garment_hd = os.path.join(example_path, 'garment/03244_00.jpg')
model_dc = os.path.join(example_path, 'model/model_8.png')
garment_dc = os.path.join(example_path, 'garment/048554_1.jpg')
openpose_model_dc.preprocessor.body_estimation.model.to('cuda')
ootd_model_dc.pipe.to('cuda')
ootd_model_dc.image_encoder.to('cuda')
ootd_model_dc.text_encoder.to('cuda')
def convert_to_image(image_array):
if isinstance(image_array, np.ndarray):
# Normalize the data to the range [0, 255]
image_array = 255 * (image_array - np.min(image_array)) / (np.max(image_array) - np.min(image_array))
# Convert to uint8
image_array = image_array.astype(np.uint8)
return Image.fromarray(image_array)
else:
# Convert to NumPy array first if necessary
image_array = np.array(image_array)
# Normalize and convert to uint8
image_array = 255 * (image_array - np.min(image_array)) / (np.max(image_array) - np.min(image_array))
image_array = image_array.astype(np.uint8)
return Image.fromarray(image_array)
# import spaces
# @spaces.GPU
def process_hd(vton_img, garm_img, n_samples, n_steps, image_scale, seed):
model_type = 'hd'
category = 0 # 0:upperbody; 1:lowerbody; 2:dress
with torch.no_grad():
openpose_model_hd.preprocessor.body_estimation.model.to('cuda')
ootd_model_hd.pipe.to('cuda')
ootd_model_hd.image_encoder.to('cuda')
ootd_model_hd.text_encoder.to('cuda')
garm_img = Image.open(garm_img).resize((768, 1024))
vton_img = Image.open(vton_img).resize((768, 1024))
keypoints = openpose_model_hd(vton_img.resize((384, 512)))
model_parse, _ = parsing_model_hd(vton_img.resize((384, 512)))
mask, mask_gray = get_mask_location(model_type, category_dict_utils[category], model_parse, keypoints)
mask = mask.resize((768, 1024), Image.NEAREST)
mask_gray = mask_gray.resize((768, 1024), Image.NEAREST)
masked_vton_img = Image.composite(mask_gray, vton_img, mask)
images = ootd_model_hd(
model_type=model_type,
category=category_dict[category],
image_garm=garm_img,
image_vton=masked_vton_img,
mask=mask,
image_ori=vton_img,
num_samples=n_samples,
num_steps=n_steps,
image_scale=image_scale,
seed=seed,
)
return images
# @spaces.GPU
def process_dc(vton_img, garm_img, category):
model_type = 'dc'
if category == 'Upper-body':
category = 0
elif category == 'Lower-body':
category = 1
else:
category =2
with torch.no_grad():
# openpose_model_dc.preprocessor.body_estimation.model.to('cuda')
# ootd_model_dc.pipe.to('cuda')
# ootd_model_dc.image_encoder.to('cuda')
# ootd_model_dc.text_encoder.to('cuda')
garm_img = Image.open(garm_img).resize((768, 1024))
vton_img = Image.open(vton_img).resize((768, 1024))
keypoints ,candidate , subset = openpose_model_dc(vton_img.resize((384, 512)))
# print(len(keypoints["pose_keypoints_2d"]))
# print(keypoints["pose_keypoints_2d"])
# person_image = np.asarray(vton_img)
# print(len(person_image))
# person_image = np.asarray(Image.open(vton_img).resize((768, 1024)))
# output = draw_bodypose(canvas=person_image,candidate=candidate, subset=subset )
# output_image = Image.fromarray(output)
# output_image.save('keypose.png')
left_point = keypoints["pose_keypoints_2d"][2]
right_point = keypoints["pose_keypoints_2d"][5]
neck_point = keypoints["pose_keypoints_2d"][1]
hip_point = keypoints["pose_keypoints_2d"][8]
print(f'left shoulder - {left_point}')
print(f'right shoulder - {right_point}')
# #find disctance using Euclidian distance
shoulder_width_pixels = round(np.sqrt( np.power((right_point[0]-left_point[0]),2) + np.power((right_point[1]-left_point[1]),2)),2)
height_pixels = round(np.sqrt( np.power((neck_point[0]-hip_point[0]),2) + np.power((neck_point[1]-hip_point[1]),2)),2) *2
# # Assuming an average human height
average_height_cm = 172.72 *1.5
# Conversion factor from pixels to cm
conversion_factor = average_height_cm / height_pixels
# Convert shoulder width to real-world units
shoulder_width_cm = shoulder_width_pixels * conversion_factor
print(f'Shoulder width (in pixels): {shoulder_width_pixels}')
print(f'Estimated height (in pixels): {height_pixels}')
print(f'Conversion factor (pixels to cm): {conversion_factor}')
print(f'Shoulder width (in cm): {shoulder_width_cm}')
print(f'Shoulder width (in INCH): {round(shoulder_width_cm/2.54,1)}')
model_parse, face_mask = parsing_model_dc(vton_img.resize((384, 512)))
model_parse_image = convert_to_image(model_parse)
face_mask_image = convert_to_image(face_mask)
# Save the images
model_parse_image.save('model_parse_image.png')
face_mask_image.save('face_mask_image.png')
mask, mask_gray = get_mask_location(model_type, category_dict_utils[category], model_parse, keypoints)
mask = mask.resize((768, 1024), Image.NEAREST)
mask_gray = mask_gray.resize((768, 1024), Image.NEAREST)
masked_vton_img = Image.composite(mask_gray, vton_img, mask)
images = ootd_model_dc(
model_type=model_type,
category=category_dict[category],
image_garm=garm_img,
image_vton=masked_vton_img,
mask=mask,
image_ori=vton_img,
num_samples=1,
num_steps=10,
image_scale= 2.0,
seed=-1,
)
return images
block = gr.Blocks().queue()
with block:
with gr.Row():
gr.Markdown("# ")
# with gr.Row():
# gr.Markdown("## Half-body-1")
# with gr.Row():
# gr.Markdown("***Support upper-body garments***")
# with gr.Row():
# with gr.Column():
# vton_img = gr.Image(label="Model", sources='upload', type="filepath", height=384, value=model_hd)
# example = gr.Examples(
# inputs=vton_img,
# examples_per_page=14,
# examples=[
# os.path.join(example_path, 'model/model_1.png'),
# os.path.join(example_path, 'model/model_2.png'),
# os.path.join(example_path, 'model/model_3.png'),
# os.path.join(example_path, 'model/model_4.png'),
# os.path.join(example_path, 'model/model_5.png'),
# os.path.join(example_path, 'model/model_6.png'),
# os.path.join(example_path, 'model/model_7.png'),
# os.path.join(example_path, 'model/01008_00.jpg'),
# os.path.join(example_path, 'model/07966_00.jpg'),
# os.path.join(example_path, 'model/05997_00.jpg'),
# os.path.join(example_path, 'model/02849_00.jpg'),
# os.path.join(example_path, 'model/14627_00.jpg'),
# os.path.join(example_path, 'model/09597_00.jpg'),
# os.path.join(example_path, 'model/01861_00.jpg'),
# ])
# with gr.Column():
# garm_img = gr.Image(label="Garment", sources='upload', type="filepath", height=384, value=garment_hd)
# example = gr.Examples(
# inputs=garm_img,
# examples_per_page=14,
# examples=[
# os.path.join(example_path, 'garment/03244_00.jpg'),
# os.path.join(example_path, 'garment/00126_00.jpg'),
# os.path.join(example_path, 'garment/03032_00.jpg'),
# os.path.join(example_path, 'garment/06123_00.jpg'),
# os.path.join(example_path, 'garment/02305_00.jpg'),
# os.path.join(example_path, 'garment/00055_00.jpg'),
# os.path.join(example_path, 'garment/00470_00.jpg'),
# os.path.join(example_path, 'garment/02015_00.jpg'),
# os.path.join(example_path, 'garment/10297_00.jpg'),
# os.path.join(example_path, 'garment/07382_00.jpg'),
# os.path.join(example_path, 'garment/07764_00.jpg'),
# os.path.join(example_path, 'garment/00151_00.jpg'),
# os.path.join(example_path, 'garment/12562_00.jpg'),
# os.path.join(example_path, 'garment/04825_00.jpg'),
# ])
# with gr.Column():
# result_gallery = gr.Gallery(label='Output', show_label=False, elem_id="gallery", preview=True, scale=1)
# with gr.Column():
# run_button = gr.Button(value="Run")
# n_samples = gr.Slider(label="Images", minimum=1, maximum=4, value=1, step=1)
# n_steps = gr.Slider(label="Steps", minimum=20, maximum=40, value=20, step=1)
# # scale = gr.Slider(label="Scale", minimum=1.0, maximum=12.0, value=5.0, step=0.1)
# image_scale = gr.Slider(label="Guidance scale", minimum=1.0, maximum=5.0, value=2.0, step=0.1)
# seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, value=-1)
# ips = [vton_img, garm_img, n_samples, n_steps, image_scale, seed]
# run_button.click(fn=process_hd, inputs=ips, outputs=[result_gallery])
with gr.Row():
gr.Markdown("## Virtual Trial Room")
with gr.Row():
gr.Markdown("*** Note :- Please Select Garment Type in below drop-down as upper-body/lower-body/dresses;***")
with gr.Row():
with gr.Column():
vton_img_dc = gr.Image(label="Model", sources='upload', type="filepath", height=384, value=model_dc)
example = gr.Examples(
label="Select for Upper/Lower Body",
inputs=vton_img_dc,
examples_per_page=7,
examples=[
os.path.join(example_path, 'model/model_8.png'),
os.path.join(example_path, 'model/049447_0.jpg'),
os.path.join(example_path, 'model/049713_0.jpg'),
os.path.join(example_path, 'model/051482_0.jpg'),
os.path.join(example_path, 'model/051918_0.jpg'),
os.path.join(example_path, 'model/051962_0.jpg'),
os.path.join(example_path, 'model/049205_0.jpg'),
]
)
example = gr.Examples(
label="Select for Full Body Dress",
inputs=vton_img_dc,
examples_per_page=7,
examples=[
os.path.join(example_path, 'model/model_9.png'),
# os.path.join(example_path, 'model/052767_0.jpg'),
# os.path.join(example_path, 'model/052472_0.jpg'),
os.path.join(example_path, 'model/053514_0.jpg'),
os.path.join(example_path, 'model/male/male_side.png'),
os.path.join(example_path, 'model/male/male_2.png'),
os.path.join(example_path, 'model/male/femal_s_34.png'),
os.path.join(example_path, 'model/male/femal_s_34_test.png'),
os.path.join(example_path, 'model/male/male_small.png'),
os.path.join(example_path, 'model/male/female.png'),
# os.path.join(example_path, 'model/053228_0.jpg'),
# os.path.join(example_path, 'model/052964_0.jpg'),
# os.path.join(example_path, 'model/053700_0.jpg'),
]
)
with gr.Column():
garm_img_dc = gr.Image(label="Garment", sources='upload', type="filepath", height=384, value=garment_dc)
category_dc = gr.Dropdown(label="Garment category (important option!!!)", choices=["Upper-body", "Lower-body", "Dress"], value="Upper-body")
example = gr.Examples(
label="Examples (upper-body)",
inputs=garm_img_dc,
examples_per_page=7,
examples=[
os.path.join(example_path,'garment/01260_00.jpg'),
os.path.join(example_path,'garment/01430_00.jpg'),
os.path.join(example_path,'garment/02783_00.jpg'),
os.path.join(example_path,'garment/03751_00.jpg'),
os.path.join(example_path,'garment/06429_00.jpg'),
os.path.join(example_path,'garment/06802_00.jpg'),
os.path.join(example_path,'garment/07429_00.jpg'),
os.path.join(example_path,'garment/08348_00.jpg'),
os.path.join(example_path,'garment/09933_00.jpg'),
os.path.join(example_path,'garment/11028_00.jpg'),
os.path.join(example_path,'garment/11351_00.jpg'),
os.path.join(example_path,'garment/11791_00.jpg'),
os.path.join(example_path, 'garment/048554_1.jpg'),
os.path.join(example_path, 'garment/049920_1.jpg'),
os.path.join(example_path, 'garment/049965_1.jpg'),
os.path.join(example_path, 'garment/049949_1.jpg'),
os.path.join(example_path, 'garment/050181_1.jpg'),
os.path.join(example_path, 'garment/049805_1.jpg'),
os.path.join(example_path, 'garment/050105_1.jpg'),
os.path.join(example_path, 'garment/male_tshirt1.png'),
])
example = gr.Examples(
label="Examples (lower-body)",
inputs=garm_img_dc,
examples_per_page=7,
examples=[
os.path.join(example_path, 'garment/051827_1.jpg'),
os.path.join(example_path, 'garment/051946_1.jpg'),
os.path.join(example_path, 'garment/051473_1.jpg'),
os.path.join(example_path, 'garment/051515_1.jpg'),
os.path.join(example_path, 'garment/051517_1.jpg'),
os.path.join(example_path, 'garment/051988_1.jpg'),
os.path.join(example_path, 'garment/051412_1.jpg'),
])
example = gr.Examples(
label="Examples (dress)",
inputs=garm_img_dc,
examples_per_page=7,
examples=[
os.path.join(example_path, 'garment/053290_1.jpg'),
os.path.join(example_path, 'garment/053744_1.jpg'),
os.path.join(example_path, 'garment/053742_1.jpg'),
os.path.join(example_path, 'garment/053786_1.jpg'),
os.path.join(example_path, 'garment/053790_1.jpg'),
os.path.join(example_path, 'garment/053319_1.jpg'),
os.path.join(example_path, 'garment/052234_1.jpg'),
])
with gr.Column():
result_gallery_dc = gr.Gallery(label='Output', show_label=False, elem_id="gallery", preview=True, scale=1)
with gr.Column():
run_button_dc = gr.Button(value="Run")
# n_samples_dc = gr.Slider(label="Images", minimum=1, maximum=4, value=1, step=1)
# n_steps_dc = gr.Slider(label="Steps", minimum=20, maximum=40, value=20, step=1)
# scale_dc = gr.Slider(label="Scale", minimum=1.0, maximum=12.0, value=5.0, step=0.1)
# image_scale_dc = gr.Slider(label="Guidance scale", minimum=1.0, maximum=5.0, value=2.0, step=0.1)
# seed_dc = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, value=-1)
ips_dc = [vton_img_dc, garm_img_dc, category_dc]
run_button_dc.click(fn=process_dc, inputs=ips_dc, outputs=[result_gallery_dc])
block.launch(server_name="0.0.0.0", server_port=7860 )