Commit Graph

25 Commits

Author SHA1 Message Date
AUTOMATIC1111 da8916f926 added torch.mps.empty_cache() to torch_gc()
changed a bunch of places that use torch.cuda.empty_cache() to use torch_gc() instead
2023-07-08 17:13:18 +03:00
AUTOMATIC1111 1bf01b73f4
Merge pull request #11046 from akx/ded-code
Remove a bunch of unused/vestigial code
2023-06-27 11:25:55 +03:00
Aarni Koskela 165ab44f03 Use os.makedirs(..., exist_ok=True) 2023-06-13 12:35:43 +03:00
Aarni Koskela ba70a220e3 Remove a bunch of unused/vestigial code
As found by Vulture and some eyes
2023-06-05 22:43:57 +03:00
AUTOMATIC 05933840f0 rename print_error to report, use it with together with package name 2023-05-31 19:56:37 +03:00
Aarni Koskela 00dfe27f59 Add & use modules.errors.print_error where currently printing exception info by hand 2023-05-29 09:17:30 +03:00
AUTOMATIC a5121e7a06 fixes for B007 2023-05-10 11:37:18 +03:00
AUTOMATIC f741a98bac imports cleanup for ruff 2023-05-10 08:43:42 +03:00
Tpinion ac4c7f05cd Filter out temporary files that will be generated if the download fails. 2023-02-24 00:42:29 +08:00
Max Audron 6b3981c068 clean up unused script_path imports 2023-01-27 14:44:34 +01:00
brkirch f4a488f585 Set device for facelib/facexlib and gfpgan
* FaceXLib/FaceLib doesn't pass the device argument to RetinaFace but instead chooses one itself and sets it to a global - in order to use a device other than its internally chosen default it is necessary to manually replace the default value
* The GFPGAN constructor needs the device argument to work with MPS or a CUDA device ID that differs from the default
2022-11-12 03:34:13 -05:00
AUTOMATIC 6c6ae28bf5 send all three of GFPGAN's and codeformer's models to CPU memory instead of just one for #1283 2022-10-04 12:32:22 +03:00
AUTOMATIC 2552204fcb fix for broken codeformer in PR 2022-09-30 11:03:00 +03:00
d8ahazard 7d5c29b674 Cleanup existing directories, fixes 2022-09-26 10:27:18 -05:00
d8ahazard 740070ea9c Re-implement universal model loading 2022-09-26 09:29:50 -05:00
Elias Oenal 3daf9cac46 Removed stray references to shared.device_codeformer. 2022-09-14 15:24:55 +03:00
Elias Oenal 26f733a026 fix for codeformer switching torch devices on metal systems. 2022-09-14 15:24:55 +03:00
AUTOMATIC 0de109c210 Codeformer face restoration not working: AttributeError: module 'modules.shared' has no attribute 'device_codeformer' #348 2022-09-12 23:24:54 +03:00
AUTOMATIC1111 11e03b9abd
Merge pull request #294 from EliasOenal/master
Fixes for mps/Metal: use of seeds, img2img, CodeFormer
2022-09-12 19:58:06 +03:00
AUTOMATIC 843b2b64fc Instance of CUDA out of memory on a low-res batch, even with --opt-split-attention-v1 (found cause) #255 2022-09-12 18:40:06 +03:00
Elias Oenal b7f95869b4 Refactored Metal/mps fixes. 2022-09-12 16:32:44 +02:00
Elias Oenal 2920ca7892 CodeFormer does not support mps/metal backend, implemented fallback to cpu backend. 2022-09-11 21:10:21 +02:00
AUTOMATIC 4d2c0c7a72 undo CodeFormer's upscaling of images with dimensions less than 512. 2022-09-10 13:53:10 +03:00
AUTOMATIC 8dcd3e57e7 a little bit of rework for extras tab 2022-09-07 13:35:02 +03:00
AUTOMATIC 6a9b33c848 codeformer support 2022-09-07 12:32:28 +03:00