|
|
import sys |
|
|
import gradio as gr |
|
|
import numpy as np |
|
|
from huggingface_hub import hf_hub_url, cached_download |
|
|
import PIL |
|
|
from PIL import Image |
|
|
import onnx |
|
|
import onnxruntime |
|
|
|
|
|
config_file_url = hf_hub_url("Jacopo/ToonClip", filename="model.onnx") |
|
|
model_file = cached_download(config_file_url) |
|
|
|
|
|
onnx_model = onnx.load(model_file) |
|
|
onnx.checker.check_model(onnx_model) |
|
|
|
|
|
opts = onnxruntime.SessionOptions() |
|
|
opts.intra_op_num_threads = 16 |
|
|
ort_session = onnxruntime.InferenceSession(model_file, sess_options=opts) |
|
|
|
|
|
input_name = ort_session.get_inputs()[0].name |
|
|
output_name = ort_session.get_outputs()[0].name |
|
|
|
|
|
def normalize(x, mean=(0., 0., 0.), std=(1.0, 1.0, 1.0)): |
|
|
|
|
|
x = np.asarray(x, dtype=np.float32) |
|
|
if len(x.shape) == 4: |
|
|
for dim in range(3): |
|
|
x[:, dim, :, :] = (x[:, dim, :, :] - mean[dim]) / std[dim] |
|
|
if len(x.shape) == 3: |
|
|
for dim in range(3): |
|
|
x[dim, :, :] = (x[dim, :, :] - mean[dim]) / std[dim] |
|
|
|
|
|
return x |
|
|
|
|
|
def denormalize(x, mean=(0., 0., 0.), std=(1.0, 1.0, 1.0)): |
|
|
|
|
|
x = np.asarray(x, dtype=np.float32) |
|
|
if len(x.shape) == 4: |
|
|
for dim in range(3): |
|
|
x[:, dim, :, :] = (x[:, dim, :, :] * std[dim]) + mean[dim] |
|
|
if len(x.shape) == 3: |
|
|
for dim in range(3): |
|
|
x[dim, :, :] = (x[dim, :, :] * std[dim]) + mean[dim] |
|
|
|
|
|
return x |
|
|
|
|
|
from PIL import Image |
|
|
|
|
|
def resize_image(image, size): |
|
|
width, height = image.size |
|
|
if max(width, height) > size: |
|
|
if width > height: |
|
|
ratio = width / size |
|
|
new_height = int(height / ratio) |
|
|
new_width = size |
|
|
else: |
|
|
ratio = height / size |
|
|
new_width = int(width / ratio) |
|
|
new_height = size |
|
|
resized_image = image.resize((new_width, new_height), Image.ANTIALIAS) |
|
|
return resized_image |
|
|
else: |
|
|
return image |
|
|
|
|
|
|
|
|
def nogan(input_img): |
|
|
input_img = resize_image(input_img, 1024) |
|
|
i = np.asarray(input_img) |
|
|
i = i.astype("float32") |
|
|
i = np.transpose(i, (2, 0, 1)) |
|
|
i = np.expand_dims(i, 0) |
|
|
i = i / 255.0 |
|
|
i = normalize(i, (0.485, 0.456, 0.406), (0.229, 0.224, 0.225)) |
|
|
|
|
|
ort_outs = ort_session.run([output_name], {input_name: i}) |
|
|
output = ort_outs |
|
|
output = output[0][0] |
|
|
|
|
|
output = denormalize(output, (0.485, 0.456, 0.406), (0.229, 0.224, 0.225)) |
|
|
output = output * 255.0 |
|
|
output = output.astype('uint8') |
|
|
output = np.transpose(output, (1, 2, 0)) |
|
|
img = PIL.Image.fromarray(output, 'RGB') |
|
|
half = 0.2 |
|
|
output_image = img.resize( [int(half * s) for s in img.size] ) |
|
|
|
|
|
|
|
|
|
|
|
return output_image |
|
|
|
|
|
title = "Zoom, Clip, Toon" |
|
|
description = """Image to Toon Using AI""" |
|
|
article = """ |
|
|
<p style='text-align: center'>The \"ToonClip\" model was trained by <a href='https://twitter.com/JacopoMangia' target='_blank'>Jacopo Mangiavacchi</a> and available at <a href='https://github.com/jacopomangiavacchi/ComicsHeroMobileUNet' target='_blank'>Github Repo ComicsHeroMobileUNet</a></p> |
|
|
<br> |
|
|
""" |
|
|
|
|
|
examples=[] |
|
|
|
|
|
iface = gr.Interface( |
|
|
nogan, |
|
|
gr.inputs.Image(type="pil", shape=(1024, 1024)), |
|
|
gr.outputs.Image(type="pil"), |
|
|
title=title, |
|
|
description=description, |
|
|
article=article, |
|
|
examples=examples) |
|
|
|
|
|
iface.launch() |
