Age | Commit message (Collapse) | Author |
|
|
|
|
|
GFPGAN and LDSR)
|
|
changed a bunch of places that use torch.cuda.empty_cache() to use torch_gc() instead
|
|
Remove a bunch of unused/vestigial code
|
|
|
|
As found by Vulture and some eyes
|
|
|
|
by hand
|
|
|
|
|
|
|
|
|
|
* 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
|
|
just one for #1283
|
|
|
|
|
|
|
|
|
|
|
|
'modules.shared' has no attribute 'device_codeformer' #348
|
|
Fixes for mps/Metal: use of seeds, img2img, CodeFormer
|
|
--opt-split-attention-v1 (found cause) #255
|
|
|
|
backend.
|
|
|
|
|
|
|