🤖🖌️ Automatically generate new textures similar to a source photograph.
Project description
neural-texturize
Automatically generate new textures similar to your source image. Useful if you want to make variations on a theme or expand the size of an existing texture.
1. Examples & Usage
The main script takes a source image as a texture, and generates a new output that captures the style of the original. Here are some examples:
texturize samples/grass.webp --size=1440x960 --output=result.png
texturize samples/gravel.png --iterations=200 --precision=1e-5
texturize samples/sand.tiff --output=tmp/{source}-{octave}.webp
texturize samples/brick.jpg --device=cpu
For details about the command-line options, see the tool itself:
texturize --help
Here are the command-line options currently available:
Usage: texturize SOURCE... [--size=WxH] [--output=FILE] [--variations=V] [--seed=SEED] [--mode=MODE] [--octaves=O] [--threshold=H] [--iterations=I] [--device=DEVICE] [--precision=PRECISION] [--quiet] [--verbose] Options: SOURCE Path to source image to use as texture. -s WxH, --size=WxH Output resolution as WIDTHxHEIGHT. [default: 640x480] -o FILE, --output=FILE Filename for saving the result, includes format variables. [default: {source}_gen{variation}.png] --variations=V Number of images to generate at same time. [default: 1] --seed=SEED Configure the random number generation. --mode=MODE Either "patch" or "gram" to specify critics. [default: gram] --octaves=O Number of octaves to process. [default: 5] --threshold=T Quality for optimization, lower is better. [default: 1e-4] --iterations=I Maximum number of iterations each octave. [default: 99] --device=DEVICE Hardware to use, either "cpu" or "cuda". --precision=PRECISION Floating-point format to use, "float16" or "float32". --quiet Suppress any messages going to stdout. --verbose Display more information on stdout. -h, --help Show this message.
2. Installation
This repository uses submodules, so you’ll need to clone it recursively to ensure dependencies are available:
git clone --recursive https://github.com/photogeniq/neural-texturize.git
Then, you can create a new virtual environment called myenv by installing Miniconda and calling the following commands, depending whether you want to run on CPU or GPU (via CUDA):
cd neural-texturize
# a) Use this if you have an *Nvidia GPU only*.
conda env create -n myenv -f tasks/setup-cuda.yml
# b) Fallback if you just want to run on CPU.
conda env create -n myenv -f tasks/setup-cpu.yml
Once the virtual environment is created, you can activate it and finish the setup of neural-texturize with these commands:
conda activate myenv
poetry install
Finally, you can check if everything worked by calling the script:
texturize
You can use conda env remove -n myenv to delete the virtual environment once you are done.
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 texturize-0.7.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2112a442db6376fb5e80137ab6c7f26c9175db4e8e2f3771fc07ad205883cda5 |
|
MD5 | 96a7dc8b55260e65c2a4f6c916315e7e |
|
BLAKE2b-256 | afbb15445aadd3ffade2cd8e0f49cb5924e012f8c0304f7455b8405d264c70d7 |