cmdr2
|
e4dd2e26ab
|
Fix torchruntime to not force cu128 on older NVIDIA GPUs (which don't support it)
|
2025-04-29 10:08:24 +05:30 |
|
cmdr2
|
40801de615
|
Tell the user to reinstall ED if they're trying to use a 50xx GPU with Python 3.8-based Easy Diffusion
|
2025-04-27 21:28:56 +05:30 |
|
cmdr2
|
adfe24fdd0
|
Fix FileNotFoundError when installing torch on Windows PCs without powershell in their system PATH variable
|
2025-04-25 20:45:14 +05:30 |
|
cmdr2
|
1ed27e63f9
|
Use pytorch 2.7 (with cuda 12.8) on new installations with NVIDIA gpus
|
2025-04-24 15:50:55 +05:30 |
|
cmdr2
|
0e3b6a8609
|
Auto-upgrade torch for NVIDIA 50xx series. Fix for #1918
|
2025-04-23 15:22:59 +05:30 |
|
cmdr2
|
16c76886fa
|
Fix for incorrect upgrade logic for torchruntime. Affects the workaround in #1918
|
2025-04-23 15:22:30 +05:30 |
|
cmdr2
|
5c7625c425
|
Fix for blackwell GPUs on new installations
|
2025-03-29 14:34:17 +05:30 |
|
cmdr2
|
4044d696e6
|
Use torchruntime with Forge
|
2025-03-11 11:03:48 +05:30 |
|
cmdr2
|
5285e8f5e8
|
Use safetensors as the default model instead of ckpt
|
2025-03-11 10:24:55 +05:30 |
|
cmdr2
|
7a9d25fb4f
|
Fix nvidia 50xx support
|
2025-03-10 06:20:46 +05:30 |
|
cmdr2
|
0b24ef71a1
|
Fix compatibility with python 3.9 and directml
|
2025-03-07 10:39:38 +05:30 |
|
cmdr2
|
24e374228d
|
Check for half-precision on GeForce MX450
|
2025-03-07 10:28:07 +05:30 |
|
cmdr2
|
9c7f84bd55
|
Fix Granite Ridge APU device type
|
2025-03-06 12:48:18 +05:30 |
|
cmdr2
|
5df082a98f
|
Recognize some more cards (5070, Granite Ridge) via a torchruntime upgrade
|
2025-03-06 12:06:13 +05:30 |
|
cmdr2
|
895801b667
|
Use 64MB dict size for NSIS compressor
|
2025-03-06 10:18:55 +05:30 |
|
cmdr2
|
f0671d407d
|
Use python 3.9 by default
|
2025-03-04 15:27:57 +05:30 |
|
cmdr2
|
64be622285
|
sdkit 2.0.22.7/2.0.15.16 - python 3.9 compatibility
|
2025-03-04 14:58:34 +05:30 |
|
cmdr2
|
80a4c6f295
|
torchruntime upgrade - fix bug with multiple GPUs of the same model
|
2025-03-04 11:27:17 +05:30 |
|
cmdr2
|
7a383d7bc4
|
sdkit upgrade - fixes loras with numpy arrays
|
2025-02-19 14:56:23 +05:30 |
|
cmdr2
|
5cddfe78b2
|
Potential fix for #1902
|
2025-02-18 11:12:46 +05:30 |
|
cmdr2
|
1ec4547a68
|
v3.5.6
|
2025-02-17 14:53:00 +05:30 |
|
cmdr2
|
827ec785e1
|
Fix broken model merge
|
2025-02-17 14:52:13 +05:30 |
|
cmdr2
|
40bcbad797
|
Recognize Phoenix3 and Phoenix4 AMD APUs
|
2025-02-13 15:21:52 +05:30 |
|
cmdr2
|
03c49d5b47
|
Hotfix for missing torchruntime on new installations
|
2025-02-10 19:31:05 +05:30 |
|
cmdr2
|
e9667fefa9
|
Temporary fix for #1899
|
2025-02-10 18:14:43 +05:30 |
|
cmdr2
|
19c6e10eda
|
Use the correct size of the image when used as the input. Code credit: @AvidGameFan
|
2025-02-10 12:49:38 +05:30 |
|
cmdr2
|
55daf647a0
|
v3.5.5 / v3.0.13 - torchruntime
|
2025-02-10 10:36:43 +05:30 |
|
cmdr2
|
077c6c3ac9
|
Use torchruntime for installing torch/torchvision on the users' PC, instead of the custom logic used here. torchruntime was built from the custom logic used here, and covers a lot more scenarios and supports more devices
|
2025-02-10 10:33:57 +05:30 |
|
cmdr2
|
d0f45f1f51
|
Another fix for mps backend
|
2025-02-10 10:04:55 +05:30 |
|
cmdr2
|
7a17adc46b
|
Fix broken mps backend
|
2025-02-10 09:55:08 +05:30 |
|
cmdr2
|
3380b58c18
|
torchruntime 1.9.2 - fixes a bug on cpu platforms
|
2025-02-08 16:14:48 +05:30 |
|
cmdr2
|
7577a1f66c
|
v3.5.4
|
2025-02-08 11:27:32 +05:30 |
|
cmdr2
|
a8b1bbe441
|
Fix a bug where the inpainting mask wasn't resized to the image size when using the WebUI/v3.5 backend. Thanks @AvidGameFan for their help in investigating and fixing this!
|
2025-02-08 11:26:03 +05:30 |
|
cmdr2
|
a1fb9bc65c
|
Revert "Merge pull request #1874 from AvidGameFan/inpaint_mask_size"
This reverts commit f737921eaafa723dc4add4a15c98e6dd04591cc3, reversing
changes made to b12a6b953775b35601e1512215c06536b8df99ee.
|
2025-02-07 10:46:03 +05:30 |
|
cmdr2
|
f737921eaa
|
Merge pull request #1874 from AvidGameFan/inpaint_mask_size
Remove inpaint size limit
|
2025-02-07 10:27:44 +05:30 |
|
cmdr2
|
b12a6b9537
|
changelog
|
2025-02-06 13:08:58 +05:30 |
|
cmdr2
|
2efef8043e
|
Remove hardcoded torch.cuda references from the webui backend code
|
2025-02-06 13:07:10 +05:30 |
|
cmdr2
|
9e21d681a0
|
Remove hardcoded references to torch.cuda; Use torchruntime and sdkit's device utilities instead
|
2025-02-06 13:06:51 +05:30 |
|
cmdr2
|
964aef6bc3
|
Fix a bug preventing the installation of the WebUI backend
|
2025-02-04 17:57:08 +05:30 |
|
cmdr2
|
07105d7cfd
|
Debug logging for webui root dir
|
2025-02-04 17:47:58 +05:30 |
|
cmdr2
|
7aa4fe9c4b
|
sdkit 2.0.22.3 or 2.0.15.12 - fixes a regression on mac
|
2025-02-03 21:29:48 +05:30 |
|
cmdr2
|
03a5108cdd
|
sdkit 2.0.22.2 or 2.0.15.11 - install torchruntime
|
2025-02-03 16:35:48 +05:30 |
|
cmdr2
|
c248231181
|
sdkit 2.0.22 or 2.0.15.9
|
2025-01-31 18:35:29 +05:30 |
|
cmdr2
|
35f752b36d
|
Move the half precision bug check logic to sdkit
|
2025-01-31 16:28:12 +05:30 |
|
cmdr2
|
d5a7c1bdf6
|
[sdkit update] v2.0.22 (and v2.0.15.8 for LTS)
|
2025-01-31 16:22:02 +05:30 |
|
cmdr2
|
d082ac3519
|
changelog
|
2025-01-28 10:34:27 +05:30 |
|
cmdr2
|
e57599c01e
|
Fix for conda accidental jailbreak when using WebUI
|
2025-01-28 10:33:25 +05:30 |
|
cmdr2
|
fd76a160ac
|
changelog
|
2025-01-28 09:53:28 +05:30 |
|
cmdr2
|
5337aa1a6e
|
Temporarily remove torch 2.5 from the list, since it doesn't work with Python 3.8. More on this in future commits
|
2025-01-28 09:51:18 +05:30 |
|
cmdr2
|
89ada5bfa9
|
Skip sdkit/diffusers install if it's in developer mode
|
2025-01-27 18:46:19 +05:30 |
|