InvokeAI/ldm/invoke/generator
Lincoln Stein cca8d14c79
defer patchmatch loading (#2039)
* defer patchmatch loading

Because of the way that patchmatch was loaded early at import time, it
was impossible to turn off the attempted loading with --no-patchmatch.

In addition, the patchmatch loading messages appear early on during
initialization, interfering with ability to print out the version
cleanly when --version provided to invoke script.

This commit creates a thin wrapper class for patch_match that is only
loaded when needed, solving both problems.

* create a singleton patchmatch object for use in inpainting

This creates a thin wrapper to patchmatch which loads the module
on demand, respecting the global "trypatchmatch" option.

* address 2d round of issues in PR 2039 comments

* Patchmatch->PatchMatch and misc cleanup
2022-12-20 15:32:35 -08:00
..
__init__.py rename all modules from ldm.dream to ldm.invoke 2022-10-08 11:37:23 -04:00
base.py Fix: define path as None before usage 2022-12-13 19:46:03 -05:00
embiggen.py Global replace [ \t]+$, add "GB" (#1751) 2022-12-19 16:36:39 +00:00
img2img.py Correct timestep for img2img initial noise addition (#1946) 2022-12-15 15:59:19 -05:00
inpaint.py defer patchmatch loading (#2039) 2022-12-20 15:32:35 -08:00
omnibus.py Global replace [ \t]+$, add "GB" (#1751) 2022-12-19 16:36:39 +00:00
txt2img2img.py Correct timestep for img2img initial noise addition (#1946) 2022-12-15 15:59:19 -05:00
txt2img.py Reduce more memories on free_gpu_mem option (#1915) 2022-12-11 13:49:55 -05:00