New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Bug]: Remove of --no-half cause errors under MacOS with any Torch version, but almost all samplers produce only noise with it and latest nightly builds #8555
Comments
I'm getting similar on my 32GB M1 Max - MacOS 13.2. Default Command Line Arguments: --upcast-sampling --no-half-vae --use-cpu interrogate Problem is with v2-1_768 (2.0, 1.5 & 1.4 work fine). With SD2.1 it errors at 0% with all sampling methods (except DDIM, PLMS & UniPC):
With DDIM, PLMS & UniPC it gets to 100% with black square and no saved image:
Have tried with all extensions off and have deleted /venv directory and get same results. Have been absorbed in controlnet with SD1.5 for a while so not sure how long has been a problem. Thanks. |
Totally , the same issue on my device. |
I have the same problem after installing the fresh torch 2.0 GA, without |
Edit: Actually, if you could give me the traceback from the error you get from using 1.14.0.dev20221025 without |
@brkirch I'm not entirely sure how to use it with 1.14.0 now because it's installed in my Conda environment and the WebUI always tries to create its own venv and install dependencies there. Maybe I can somehow force WebUI to skip creating another venv? Before that I used the old version, which I deleted |
So just tested some more torch versions from nightly and the earliest versio (torch-2.0.0.dev20230128 torchvision-0.15.0.dev20230128) showed the same effects for me, as the latest one (torch-2.1.0.dev20230327 torchvision-0.16.0.dev2023032). |
@brkirch For DPM++ 2M/SDE Karras/non-Karras:
For DDIM:
|
me too |
have you solved this ? i also have the problem |
I also met the same problem, can you tell me you solved? thanks |
me too!! how to solve this? |
Me too! In my Apple M1 Pro 16G. |
Try torch 1.12.1 |
Still not work for me. |
I think there is something broken in Ventura. I can use torch 1.12 and 1.13 with no problems in Monterey (I tested rx 570 8Gb and rx 6800 xt), also torch 2.x works correctly if you launch SD with the |
It may relate to the nightly PyTorch version. I encountered the same issue and tried revert back to my older version and problem solved! |
我也是 |
edit “stable-diffusion-webui/webui-user.sh” find COMMANDLINE_ARGS variable Use the following configuration: |
Hi @ZXBmmt it worked for me! Thank you! (Apple M1 Pro) |
I updated to MacOS 13.3.1 and installed latest commit [5ab7f21], but unfortunately things got even worse. Now even the DDIM sampler produces wrong images without --no-half |
It's not worked。。 |
Same issue, MacOS Monterey (12.6.2 (21G320)) on |
it works for macbook m1, thanks |
Open webui-macos-env.sh file with your textedit. Change : To : |
Thanks, It worked. There is Another solution without change any files, That is use the Start command line: |
great, you re very clever! |
Open webui-macos-env.sh file with your textedit. Change : To : 第二种解决方案: |
Hi @ZXBmmt it worked for me (MacOS 13.2.1 16G commit baf6946) Thank you! (Apple M1 Pro) |
Thank you so much! It worked. |
./webui.sh --no-half 我这样解决了 |
thank you!! |
Thanks, this worked for me to fix the error. I didn't need the part --use-cpu all. This runs on the CPU and is slower than the GPU. It's not as slow on the CPU as I thought it would be though and it only seems to use half of my CPU. Time for the same 512x512 image was 1:20 with CPU and 0:20 with M1 Max GPU. This is roughly the same time as my Nvidia 3060 mobile GPU. The Nvidia GPU has the fan running loud but the M1 Max barely gets warm. Even after hundreds of images, there was no fan noise at all. This is great that I can use Stable Diffusion on the Mac and models like OpenJourney are working the same as they do on Windows. |
What were your command line args, if you don't mind? |
I used: export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --opt-split-attention --lowvram --no-half" |
This is the correct solution, according to how you are 'supposed' to do it: Open Replace the line that says: #export COMMANDLINE_ARGS="" With: export COMMANDLINE_ARGS="$COMMANDLINE_ARGS --no-half" Then everything works great! |
you help a lot. Thanks. MacOS 12.6.6, Intel. |
I had |
Is there an existing issue for this?
What happened?
I've tested different versions of Torch to possibly find one that works with --no-half but no luck.
1.14.0.dev20221025 I'm currently using works fine but throws errors without the --ho-half argument. The latest nightly version 2.1.0.dev20230312 seems to work with this argument and gives a really noticeable performance boost, but almost all samplers break on it.
My results
With --no-half:
There are no errors, but all samplers apart from DDIM and PLMS produce only noise as final results, these two gives out normal pictures. Also new UniPC produce something that looks like a bit less then noise, but still really messy.
Without --no-half:
Errors while using everything except DDIM and PLMS. They also works around 40% faster then with --no-half.
Without --no-half and with --disable-nan-check:
Just black images instead of noise.
Steps to reproduce the problem
I was just changing startup arguments
What should have happened?
Other samplers should work too, I guess
Commit where the problem happens
3c922d9
What platforms do you use to access the UI ?
MacOS
What browsers do you use to access the UI ?
Mozilla Firefox
Command Line Arguments
List of extensions
No
Console logs
Additional information
Intel Mac with RX 6600XT, MacOS 13.2.1
The text was updated successfully, but these errors were encountered: