import runway
from run import restore
from PIL import Image
@runway.command(
'translate',
inputs={
'source_imgs':
runway.image(description='input image to be translated'),
'scratch_remove':
runway.boolean(default=False, description='remove scratches'),
},
outputs={'image': runway.image(description='out image after restoration')})
def translate(model, inputs):
image = restore(inputs['source_imgs'], inputs['scratch_remove'])
im = Image.open(open(image, 'rb'))
return im
if __name__ == '__main__':
runway.run(port=8889)
import runway
import cv2
import torch
import numpy as np
import download_checkpoint
from PIL import Image
@runway.command(
'translate',
inputs={
'source_imgs':
runway.image(description='input image to be translated'),
'large': runway.boolean(default=True, description='use large model'),
},
outputs={
'image':
runway.image(
description='output image containing the translated result')
})
def translate(midas, inputs):
cv_image = np.array(inputs['source_imgs'])
img = cv2.cvtColor(cv_image, cv2.COLOR_BGR2RGB)
if inputs['large']:
transform = download_checkpoint.transforml
input_batch = transform(img)
midas = download_checkpoint.midasl
else:
transform = download_checkpoint.transformS
input_batch = transform(img)
midas = download_checkpoint.midasS
@runway.setup(options={'checkpoint': runway.file(extension='.pth')})
def setup(opts):
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
net = _load_model(MODEL, opts['checkpoint'])
return Predictor(net, device)
inputs = {
'composite_image':
runway.image,
'foreground_mask':
runway.image,
'transfer_color':
runway.boolean(
default=True,
description=
"Transfer colors back to source image for high-resolution output"),
'transfer_resolution':
runway.number(default=512,
min=256,
max=1024,
step=128,
description="Which resolution to transfer colors from")
}
outputs = {'harmonized_image': runway.image}
@runway.command('harmonize', inputs=inputs, outputs=outputs)
def harmonize(model, inputs):
def generate_image(generator, latent_vector):
latent_vector = latent_vector.reshape((1, 18, 512))
generator.set_dlatents(latent_vector)
img_array = generator.generate_images()[0]
img = PIL.Image.fromarray(img_array, 'RGB')
return img.resize((512, 512))
# ENCODING
generate_inputs_1 = {
'portrait': runway.image(),
'iterations': runway.number(min=1, max=5000, default=10, step=1.0),
'encode': runway.boolean(default=False)
}
generate_outputs_1 = {'image': runway.image(width=512, height=512)}
encodeCount = 0
latent_vectors = []
# latent_vectors.append(preLoad1)
# latent_vectors.append(preLoad2)
# latent_vectors.append(preLoad1)
# latent_vectors.append(preLoad2)
@runway.command('encode', inputs=generate_inputs_1, outputs=generate_outputs_1)
def find_in_space(model, inputs):
global generated_dlatents
global prevIterations
import runway
import numpy as np
import argparse
import torch
from process_order import draw
import os
from PIL import Image
import shutil
@runway.command('translate', inputs={'source_imgs': runway.image(description='input image to be translated'), runway.boolean(default=True),}, outputs={'image': runway.image(description='output image containing the translated result')})
def translate(learn, inputs):
os.makedirs('images', exist_ok=True)
inputs['source_imgs'].save('images/temp.jpg')
paths = os.path.join('images','temp.jpg')
draw(paths)
pathout = "./output/temp/result.jpg"
img = Image.open(open(pathout, 'rb'))
shutil.rmtree('./output/')
return img
if __name__ == '__main__':
runway.run(port=8889)