aboutsummaryrefslogtreecommitdiffstats
path: root/modules/gfpgan_model.py
Commit message (Expand)AuthorAgeFilesLines
* Merge branch 'master' into cpu-cmdline-optbrkirch2022-10-041-3/+13
|\
| * send all three of GFPGAN's and codeformer's models to CPU memory instead of j...AUTOMATIC2022-10-041-2/+12
* | Merge branch 'master' into masterbrkirch2022-10-041-5/+1
|\|
| * use existing function for gfpganAUTOMATIC2022-10-031-5/+1
* | When device is MPS, use CPU for GFPGAN insteadbrkirch2022-10-011-3/+3
|/
* remove unwanted formatting/functionality from the PRAUTOMATIC2022-09-301-9/+3
* Holy $hit.d8ahazard2022-09-291-18/+40
* Re-implement universal model loadingd8ahazard2022-09-261-31/+29
* gfpgan: just download the damn modelAUTOMATIC2022-09-231-6/+13
* Instance of CUDA out of memory on a low-res batch, even with --opt-split-att...AUTOMATIC2022-09-121-5/+10
* codeformer supportAUTOMATIC2022-09-071-2/+18
* option to unload GFPGAN after usingAUTOMATIC2022-09-031-3/+12
* split codebase into multiple files; to anyone this affects negatively: sorryAUTOMATIC2022-09-031-0/+58