from PIL import Image
import torch

from transformers import AutoModel, AutoImageProcessor

REPO_NAME = "p1atdev/MangaLineExtraction-hf"

model = AutoModel.from_pretrained(REPO_NAME, trust_remote_code=True)
processor = AutoImageProcessor.from_pretrained(REPO_NAME, trust_remote_code=True)

image = Image.open("./sample.jpg")

inputs = processor(image, return_tensors="pt")

with torch.no_grad():
    outputs = model(inputs.pixel_values)

line_image = Image.fromarray(outputs.pixel_values[0].numpy().astype("uint8"), mode="L")
line_image.save("./line_image.png")

or you can use the pipeline

from transformers import pipeline

pipe = pipeline("image-to-image", model="p1atdev/MangaLineExtraction-hf", trust_remote_code=True)
pipe("sample.jpg")

`sample.jpg`	Generated line image
Source image	Generated line image

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: Chengze Li, Xueting Liu, Tien-Tsin Wong
Converted by: Plat
License: MIT

Model Sources

Repository: https://github.com/ljsabc/MangaLineExtraction_PyTorch
Paper: https://ttwong12.github.io/papers/linelearn/linelearn.pdf
Project page: https://www.cse.cuhk.edu.hk/~ttwong/papers/linelearn/linelearn.html

Citation

BibTeX:

bibtex

@article{li-2017-deep,
    author   = {Chengze Li and Xueting Liu and Tien-Tsin Wong},
    title    = {Deep Extraction of Manga Structural Lines},
    journal  = {ACM Transactions on Graphics (SIGGRAPH 2017 issue)},
    month    = {July},
    year     = {2017},
    volume   = {36},
    number   = {4},
    pages    = {117:1--117:12},
}