Image Composition Toolbox
Project description
libcom: everything about image composition
Introduction
libcom is an image composition toolbox covering various related tasks, including naive image composition, image blending, color transfer, image harmonization, painterly harmonization, object placement, etc.
Usage
Create runtime environment
git clone https://github.com/bcmi/libcom.git
cd libcom/requirements
conda env create -f libcom.yaml
conda activate Libcom
pip install -r runtime.txt # -i https://pypi.tuna.tsinghua.edu.cn/simple
# install a specific version of taming-transformers from source code
cd ../libcom/controllable_composition/source/ControlCom/src/taming-transformers
python setup.py install
Installation
pip install libcom
or
python setup.py install
After that, you can verify the installation by running:
cd tests
sh run_all_tests.sh
The visualization results can be found in results
folder.
Download pretrained models
During using the toolbox, the pretrained models and related files will be automatically downloaded to the installation directory. Note downloading the pretrained models may take some time when you first call some models, especially ControlComModel
and PainterlyHarmonizationModel
.
Alternatively, you can download these files from [Modelscope] or [Huggingface] in advance, and move them to the installation directory.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for libcom-0.0.1.post2-cp38-cp38-manylinux1_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8abdaab84c810fd1ba8211d016f6f29a2b27b1888e7f72f06a42efa07650d77b |
|
MD5 | 57270606853e2ae45cec642a3c9fcb8f |
|
BLAKE2b-256 | 291d43107ef204a714200c452ffff199feb185aa20e677b298ba774693158393 |