46b0d230e7
add comment for #4407 and remove seemingly unnecessary cudnn.enabled
3 years ago
2651267e3a
fix #4407 breaking UI entirely for card other than ones related to the PR
3 years ago
681c0003df
Merge pull request #4407 from yoinked-h/patch-1
...
Fix issue with 16xx cards
3 years ago
0fddb4a1c0
Rework MPS randn fix, add randn_like fix
...
torch.manual_seed() already sets a CPU generator, so there is no reason to create a CPU generator manually. torch.randn_like also needs a MPS fix for k-diffusion, but a torch hijack with randn_like already exists so it can also be used for that.
3 years ago
cc90dcc933
Merge pull request #4918 from brkirch/pytorch-fixes
...
Fixes for PyTorch 1.12.1 when using MPS
3 years ago
5b2c316890
eliminate duplicated code from #5095
3 years ago
c67c40f983
torch.cuda.empty_cache() defaults to cuda:0 device unless explicitly set otherwise first. Updating torch_gc() to use the device set by --device-id if specified to avoid OOM edge cases on multi-GPU systems.
3 years ago
e247b7400a
Add fixes for PyTorch 1.12.1
...
Fix typo "MasOS" -> "macOS"
If MPS is available and PyTorch is an earlier version than 1.13:
* Monkey patch torch.Tensor.to to ensure all tensors sent to MPS are contiguous
* Monkey patch torch.nn.functional.layer_norm to ensure input tensor is contiguous (required for this program to work with MPS on unmodified PyTorch 1.12.1)
3 years ago
abfa22c16f
Revert "MPS Upscalers Fix"
...
This reverts commit 768b95394a8500da639b947508f78296524f1836.
3 years ago
0ab0a50f9a
change formatting to match the main program in devices.py
3 years ago
1130d5df66
Update devices.py
3 years ago
76ab31e188
Fix wrong mps selection below MasOS 12.3
3 years ago
62e9fec3df
actual better fix
...
thanks C43H66N12O12S2
3 years ago
29eff4a194
terrible hack
3 years ago
cd6c55c1ab
16xx card fix
...
cudnn
3 years ago
faed465a0b
MPS Upscalers Fix
...
Get ESRGAN, SCUNet, and SwinIR working correctly on MPS by ensuring memory is contiguous for tensor views before sending to MPS device.
3 years ago
4c24347e45
Remove BSRGAN from --use-cpu, add SwinIR
3 years ago
50b5504401
remove parsing command line from devices.py
3 years ago
57eb54b838
implement CUDA device selection by ID
3 years ago
fdef8253a4
Add 'interrogate' and 'all' choices to --use-cpu
...
* Add 'interrogate' and 'all' choices to --use-cpu
* Change type for --use-cpu argument to str.lower, so that choices are case insensitive
3 years ago
7349088d32
--no-half-vae
3 years ago
e9e2a7ec9a
Merge branch 'master' into cpu-cmdline-opt
3 years ago
6c6ae28bf5
send all three of GFPGAN's and codeformer's models to CPU memory instead of just one for #1283
3 years ago
27ddc24fde
Add BSRGAN to --add-cpu
3 years ago
eeab7aedf5
Add --use-cpu command line option
...
Remove MPS detection to use CPU for GFPGAN / CodeFormer and add a --use-cpu command line option.
3 years ago
b88e4ea7d6
Merge branch 'master' into master
3 years ago
820f1dc96b
initial support for training textual inversion
3 years ago
bdaa36c844
When device is MPS, use CPU for GFPGAN instead
...
GFPGAN will not work if the device is MPS, so default to CPU instead.
3 years ago
9d40212485
first attempt to produce crrect seeds in batch
3 years ago
c7e0e28ccd
changes for #294
3 years ago
b70b51cc72
Allow TF32 in CUDA for increased performance #279
3 years ago
8fb9c57ed6
add half() supporrt for CLIP interrogation
3 years ago
f194457229
CLIP interrogator
3 years ago
b5d1af11b7
Modular device management
3 years ago
AUTOMATIC
brkirch
Matthew McGoogan
源文雨
pepe10-gpu
Extraltodeus
Abdullah Barhoum