PatchMatch
PatchMatch is an algorithm used to infill images. It can greatly improve outpainting results. PyPatchMatch is a python wrapper around a C++ implementation of the algorithm.
It uses the image data around the target area as a reference to generate new image data of a similar character and quality.
Why Use PatchMatch#
In the context of image generation, "outpainting" refers to filling in a transparent area using AI-generated image data. But the AI can't generate without some initial data. We need to first fill in the transparent area with something.
The first step in "outpainting" then, is to fill in the transparent area with something. Generally, you get better results when that initial infill resembles the rest of the image.
Because PatchMatch generates image data so similar to the rest of the image, it works very well as the first step in outpainting, typically producing better results than other infill methods supported by Invoke (e.g. LaMA, cv2 infill, random tiles).
Performance Caveat#
PatchMatch is CPU-bound, and the amount of time it takes increases proportionally as the infill area increases. While the numbers certainly vary depending on system specs, you can expect a noticeable slowdown once you start infilling areas around 512x512 pixels. 1024x1024 pixels can take several seconds to infill.
Installation#
Unfortunately, installation can be somewhat challenging, as it requires some things that pip
cannot install for you.
Windows#
You're in luck! On Windows platforms PyPatchMatch will install automatically on Windows systems with no extra intervention.
Macintosh#
You need to have opencv installed so that pypatchmatch can be built:
The next time you start invoke
, after successfully installing opencv, pypatchmatch will be built.
Linux#
Prior to installing PyPatchMatch, you need to take the following steps:
Debian Based Distros#
- Install the
build-essential
tools:
- Install
opencv
:
-
Activate the environment you use for invokeai, either with
conda
or with a virtual environment. -
Install pypatchmatch:
- Confirm that pypatchmatch is installed. At the command-line prompt enter
python
, and then at the>>>
line typefrom patchmatch import patch_match
: It should look like the following:
Python 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> from patchmatch import patch_match
Compiling and loading c extensions from "/home/lstein/Projects/InvokeAI/.invokeai-env/src/pypatchmatch/patchmatch".
rm -rf build/obj libpatchmatch.so
mkdir: created directory 'build/obj'
mkdir: created directory 'build/obj/csrc/'
[dep] csrc/masked_image.cpp ...
[dep] csrc/nnf.cpp ...
[dep] csrc/inpaint.cpp ...
[dep] csrc/pyinterface.cpp ...
[CC] csrc/pyinterface.cpp ...
[CC] csrc/inpaint.cpp ...
[CC] csrc/nnf.cpp ...
[CC] csrc/masked_image.cpp ...
[link] libpatchmatch.so ...
Arch Based Distros#
- Install the
base-devel
package:
- Install
opencv
andblas
:
or for CUDA support
- Fix the naming of the
opencv
package configuration file:
Next, Follow Steps 4-6 from the Debian Section above
If you see no errors you're ready to go!