[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

Vitkarus · 2023-03-12T17:46:39Z

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

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

--opt-sub-quad-attention --skip-torch-cuda-test --upcast-sampling --use-cpu interrogate --no-half

List of extensions

No

Console logs

Error completing request
Arguments: ('task(9rr6te8wtxyte2o)', 'watermelon', '', [], 20, 16, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
  File "/stable-diffusion-webui/modules/call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "/stable-diffusion-webui/modules/call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "/stable-diffusion-webui/modules/txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "/stable-diffusion-webui/modules/processing.py", line 486, in process_images
    res = process_images_inner(p)
  File "/stable-diffusion-webui/modules/processing.py", line 635, in process_images_inner
    samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts)
  File "/stable-diffusion-webui/modules/processing.py", line 835, in sample
    samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
  File "/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 351, in sample
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 227, in launch_sampling
    return func()
  File "/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 351, in <lambda>
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/sampling.py", line 553, in sample_dpmpp_sde
    denoised = model(x, sigmas[i] * s_in, **extra_args)
  File "/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 145, in forward
    devices.test_for_nans(x_out, "unet")
  File "/stable-diffusion-webui/modules/devices.py", line 152, in test_for_nans
    raise NansException(message)

modules.devices.NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.

Additional information

Intel Mac with RX 6600XT, MacOS 13.2.1

The text was updated successfully, but these errors were encountered:

Homemaderobot · 2023-03-14T11:06:12Z

I'm getting similar on my 32GB M1 Max - MacOS 13.2.
Torch v1.12.1
Commit a9fed7c

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):

Error completing request
Arguments: ('task(ou61msdjo5m7nj1)', 'photo of a man', '', [], 10, 15, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 768, 768, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
  File "/Users/js/stable-diffusion-webui/modules/call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "/Users/js/stable-diffusion-webui/modules/call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "/Users/js/stable-diffusion-webui/modules/txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "/Users/js/stable-diffusion-webui/modules/processing.py", line 486, in process_images
    res = process_images_inner(p)
  File "/Users/js/stable-diffusion-webui/modules/processing.py", line 636, in process_images_inner
    samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts)
  File "/Users/js/stable-diffusion-webui/modules/processing.py", line 836, in sample
    samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
  File "/Users/js/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 351, in sample
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "/Users/js/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 227, in launch_sampling
    return func()
  File "/Users/js/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 351, in <lambda>
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "/Users/js/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/Users/js/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/sampling.py", line 594, in sample_dpmpp_2m
    denoised = model(x, sigmas[i] * s_in, **extra_args)
  File "/Users/js/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/Users/js/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 145, in forward
    devices.test_for_nans(x_out, "unet")
  File "/Users/js/stable-diffusion-webui/modules/devices.py", line 152, in test_for_nans
    raise NansException(message)
modules.devices.NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.

With DDIM, PLMS & UniPC it gets to 100% with black square and no saved image:

Error completing request:41,  1.36s/it]
Arguments: ('task(ao35ifugi48be7m)', 'photo of a man', '', [], 10, 19, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 768, 768, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
  File "/Users/js/stable-diffusion-webui/modules/call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "/Users/js/stable-diffusion-webui/modules/call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "/Users/js/stable-diffusion-webui/modules/txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "/Users/js/stable-diffusion-webui/modules/processing.py", line 486, in process_images
    res = process_images_inner(p)
  File "/Users/js/stable-diffusion-webui/modules/processing.py", line 640, in process_images_inner
    devices.test_for_nans(x, "vae")
  File "/Users/js/stable-diffusion-webui/modules/devices.py", line 152, in test_for_nans
    raise NansException(message)
modules.devices.NansException: A tensor with all NaNs was produced in VAE. Use --disable-nan-check commandline argument to disable this check.

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.

yuhuihu · 2023-03-16T05:55:03Z

I'm getting similar on my 32GB M1 Max - MacOS 13.2. Torch v1.12.1 Commit a9fed7c

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):

Error completing request
Arguments: ('task(ou61msdjo5m7nj1)', 'photo of a man', '', [], 10, 15, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 768, 768, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
  File "/Users/js/stable-diffusion-webui/modules/call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "/Users/js/stable-diffusion-webui/modules/call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "/Users/js/stable-diffusion-webui/modules/txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "/Users/js/stable-diffusion-webui/modules/processing.py", line 486, in process_images
    res = process_images_inner(p)
  File "/Users/js/stable-diffusion-webui/modules/processing.py", line 636, in process_images_inner
    samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts)
  File "/Users/js/stable-diffusion-webui/modules/processing.py", line 836, in sample
    samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
  File "/Users/js/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 351, in sample
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "/Users/js/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 227, in launch_sampling
    return func()
  File "/Users/js/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 351, in <lambda>
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "/Users/js/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/Users/js/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/sampling.py", line 594, in sample_dpmpp_2m
    denoised = model(x, sigmas[i] * s_in, **extra_args)
  File "/Users/js/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/Users/js/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 145, in forward
    devices.test_for_nans(x_out, "unet")
  File "/Users/js/stable-diffusion-webui/modules/devices.py", line 152, in test_for_nans
    raise NansException(message)
modules.devices.NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.

With DDIM, PLMS & UniPC it gets to 100% with black square and no saved image:

Error completing request:41,  1.36s/it]
Arguments: ('task(ao35ifugi48be7m)', 'photo of a man', '', [], 10, 19, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 768, 768, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
  File "/Users/js/stable-diffusion-webui/modules/call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "/Users/js/stable-diffusion-webui/modules/call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "/Users/js/stable-diffusion-webui/modules/txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "/Users/js/stable-diffusion-webui/modules/processing.py", line 486, in process_images
    res = process_images_inner(p)
  File "/Users/js/stable-diffusion-webui/modules/processing.py", line 640, in process_images_inner
    devices.test_for_nans(x, "vae")
  File "/Users/js/stable-diffusion-webui/modules/devices.py", line 152, in test_for_nans
    raise NansException(message)
modules.devices.NansException: A tensor with all NaNs was produced in VAE. Use --disable-nan-check commandline argument to disable this check.

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.

Scaperista · 2023-03-17T16:12:22Z

I have the same problem after installing the fresh torch 2.0 GA, without --no-halfs I get the
input types 'tensor<1x77x1xf16>' and 'tensor<1xf32>' are not broadcast compatible
and with --no-halfs most of the samplers just produce some gibberish images with noise.
This is on an non M1 Mac running macOS 12.6.3.
Before the torch upgrade everything worked quite well aside from some random MPS problems regarding memory watermarks.

brkirch · 2023-03-22T23:31:04Z

1.14.0.dev20221025 I'm currently using works fine but throws errors without the --ho-half argument.

So all samplers work correctly with that build? Would you be able to test builds from the dates in between that and 2.1.0.dev20230312 to determine the latest build that works correctly? I haven’t been able to reproduce this issue but if I knew the exact date of the last working PyTorch build then I could likely determine more about this issue and make a workaround.

Edit: Actually, if you could give me the traceback from the error you get from using 1.14.0.dev20221025 without --no-half, that may give me a better idea of what is going wrong.

Vitkarus · 2023-03-25T14:51:14Z

@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

Scaperista · 2023-03-28T10:10:15Z

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).
Without --no-halfs I get for the latest nightly: RuntimeError: "upsample_nearest2d_channels_last" not implemented for 'Half' and with --no-halfs only noise is generated as image e.g. when using the euler sampler.

Awethon · 2023-03-29T21:51:43Z

@brkirch
Same for me, just pulled master branch and updated dependencies.
webui config is default
2.1_768 model, stable torch 2.0, M1 Max.

For DPM++ 2M/SDE Karras/non-Karras:

  |  File "/Users/username/Documents/stable-diffusion-webui/modules/txt2img.py", line 56, in txt2img
  |    processed = process_images(p)
  |  File "/Users/username/Documents/stable-diffusion-webui/modules/processing.py", line 503, in process_images
  |    res = process_images_inner(p)
  |  File "/Users/username/Documents/stable-diffusion-webui/modules/processing.py", line 653, in process_images_inner
  |    samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts)
  |  File "/Users/username/Documents/stable-diffusion-webui/modules/processing.py", line 869, in sample
  |    samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
  |  File "/Users/username/Documents/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 358, in sample
  |    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  |  File "/Users/username/Documents/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 234, in launch_sampling
  |    return func()
  |  File "/Users/username/Documents/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 358, in <lambda>
  |    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  |  File "/Users/username/Documents/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
  |    return func(*args, **kwargs)
  |  File "/Users/username/Documents/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/sampling.py", line 128, in sample_euler
  |    denoised = model(x, sigma_hat * s_in, **extra_args)
  |  File "/Users/username/Documents/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
  |    return forward_call(*args, **kwargs)
  |  File "/Users/username/Documents/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 152, in forward
  |    devices.test_for_nans(x_out, "unet")
  |  File "/Users/username/Documents/stable-diffusion-webui/modules/devices.py", line 152, in test_for_nans
  |    raise NansException(message)
  |modules.devices.NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.

For DDIM:

  File "/Users/username/Documents/stable-diffusion-webui/modules/txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "/Users/username/Documents/stable-diffusion-webui/modules/processing.py", line 503, in process_images
    res = process_images_inner(p)
  File "/Users/username/Documents/stable-diffusion-webui/modules/processing.py", line 657, in process_images_inner
    devices.test_for_nans(x, "vae")
  File "/Users/username/Documents/stable-diffusion-webui/modules/devices.py", line 152, in test_for_nans
    raise NansException(message)
modules.devices.NansException: A tensor with all NaNs was produced in VAE. Use --disable-nan-check commandline argument to disable this check.

imtiger · 2023-03-31T10:53:35Z

I have the same problem after installing the fresh torch 2.0 GA, without --no-halfs I get the input types 'tensor<1x77x1xf16>' and 'tensor<1xf32>' are not broadcast compatible and with --no-halfs most of the samplers just produce some gibberish images with noise. This is on an non M1 Mac running macOS 12.6.3. Before the torch upgrade everything worked quite well aside from some random MPS problems regarding memory watermarks.

me too

imtiger · 2023-03-31T10:55:20Z

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). Without --no-halfs I get for the latest nightly: RuntimeError: "upsample_nearest2d_channels_last" not implemented for 'Half' and with --no-halfs only noise is generated as image e.g. when using the euler sampler.

have you solved this ? i also have the problem

GoJerry · 2023-04-09T06:29:08Z

RuntimeError

I also met the same problem, can you tell me you solved? thanks
Macos M1

GoJerry · 2023-04-09T06:31:42Z

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). Without --no-halfs I get for the latest nightly: RuntimeError: "upsample_nearest2d_channels_last" not implemented for 'Half' and with --no-halfs only noise is generated as image e.g. when using the euler sampler.

have you solved this ? i also have the problem

me too!! how to solve this?

hstk30 · 2023-04-11T01:13:54Z

Error completing request
Arguments: ('task(vim8g0n4kh0utdt)', 'create a classic woman with the pearl necklace', '', [], 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
  File "/Users/hstk/code_ground/source_code/stable-diffusion-webui/modules/call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "/Users/hstk/code_ground/source_code/stable-diffusion-webui/modules/call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "/Users/hstk/code_ground/source_code/stable-diffusion-webui/modules/txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "/Users/hstk/code_ground/source_code/stable-diffusion-webui/modules/processing.py", line 503, in process_images
    res = process_images_inner(p)
  File "/Users/hstk/code_ground/source_code/stable-diffusion-webui/modules/processing.py", line 653, in process_images_inner
    samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts)
  File "/Users/hstk/code_ground/source_code/stable-diffusion-webui/modules/processing.py", line 869, in sample
    samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
  File "/Users/hstk/code_ground/source_code/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 358, in sample
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "/Users/hstk/code_ground/source_code/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 234, in launch_sampling
    return func()
  File "/Users/hstk/code_ground/source_code/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 358, in <lambda>
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "/Users/hstk/code_ground/source_code/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/Users/hstk/code_ground/source_code/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/sampling.py", line 145, in sample_euler_ancestral
    denoised = model(x, sigmas[i] * s_in, **extra_args)
  File "/Users/hstk/code_ground/source_code/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "/Users/hstk/code_ground/source_code/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 152, in forward
    devices.test_for_nans(x_out, "unet")
  File "/Users/hstk/code_ground/source_code/stable-diffusion-webui/modules/devices.py", line 152, in test_for_nans
    raise NansException(message)
modules.devices.NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.

Me too! In my Apple M1 Pro 16G.

FreeBlues · 2023-04-11T13:03:04Z

Try torch 1.12.1
Someone said that the 1.12.1 is the only version can work on Mac, other version all have issue.

hstk30 · 2023-04-11T13:36:51Z

Try torch 1.12.1 Someone said that the 1.12.1 is the only version can work on Mac, other version all have issue.

Still not work for me.

digital-pers0n · 2023-04-20T09:39:01Z

Try torch 1.12.1 Someone said that the 1.12.1 is the only version can work on Mac, other version all have issue.

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 --cpu all .
In Ventura nothing is working for me.

ZhelenZ · 2023-04-28T14:49:46Z

It may relate to the nightly PyTorch version. I encountered the same issue and tried revert back to my older version and problem solved!
Check out this link below. It well explained how and why : )
#7453 (comment)

congzai520 · 2023-05-05T12:48:19Z

我也是

ZXBmmt · 2023-05-07T02:29:56Z

edit “stable-diffusion-webui/webui-user.sh”

find COMMANDLINE_ARGS variable

Use the following configuration：
export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --opt-split-attention --lowvram --no-half --use-cpu all"

oivoodoo · 2023-05-07T10:42:36Z

Hi @ZXBmmt

it worked for me!

Thank you!

(Apple M1 Pro)

Vitkarus · 2023-05-07T14:19:05Z

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

iWooda · 2023-05-16T18:07:06Z

edit “stable-diffusion-webui/webui-user.sh”

find COMMANDLINE_ARGS variable

Use the following configuration： export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --opt-split-attention --lowvram --no-half --use-cpu all"

It's not worked。。

ctrlaltdylan · 2023-05-19T18:56:06Z

Same issue, MacOS Monterey (12.6.2 (21G320)) on master branch.

huanDreamer · 2023-05-31T00:58:01Z

edit “stable-diffusion-webui/webui-user.sh”

find COMMANDLINE_ARGS variable

Use the following configuration： export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --opt-split-attention --lowvram --no-half --use-cpu all"

it works for macbook m1, thanks

finalcolor · 2023-06-03T05:47:30Z

Open webui-macos-env.sh file with your textedit.

Change :
export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --no-half-vae --use-cpu interrogate"

To :
export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --no-half-vae --no-half --use-cpu interrogate"

iWooda · 2023-06-03T06:13:58Z

Open webui-macos-env.sh file with your textedit.

Change : export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --no-half-vae --use-cpu interrogate"

To : export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --no-half-vae --no-half --use-cpu interrogate"

Thanks, It worked. There is Another solution without change any files, That is use the Start command line:
./webui.sh --precision full --no-half Also worked for me.

finalcolor · 2023-06-03T06:53:29Z

great, you re very clever!

finalcolor · 2023-06-03T06:55:07Z

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). Without --no-halfs I get for the latest nightly: RuntimeError: "upsample_nearest2d_channels_last" not implemented for 'Half' and with --no-halfs only noise is generated as image e.g. when using the euler sampler.

have you solved this ? i also have the problem

Open webui-macos-env.sh file with your textedit.

Change :
export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --no-half-vae --use-cpu interrogate"

To :
export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --no-half-vae --no-half --use-cpu interrogate"

第二种解决方案：
That is use the Start command line:
./webui.sh --precision full --no-half

Muscleape · 2023-06-06T02:59:35Z

edit “stable-diffusion-webui/webui-user.sh”

find COMMANDLINE_ARGS variable

Use the following configuration： export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --opt-split-attention --lowvram --no-half --use-cpu all"

Hi @ZXBmmt

it worked for me （MacOS 13.2.1 16G commit baf6946）

Thank you!

(Apple M1 Pro)

howyeah · 2023-06-06T22:51:21Z

Open webui-macos-env.sh file with your textedit.
Change : export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --no-half-vae --use-cpu interrogate"
To : export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --no-half-vae --no-half --use-cpu interrogate"

Thanks, It worked. There is Another solution without change any files, That is use the Start command line: ./webui.sh --precision full --no-half Also worked for me.

Thank you so much! It worked.

befriend1314 · 2023-06-07T08:32:05Z

./webui.sh --no-half

我这样解决了

matto80 · 2023-06-09T23:39:09Z

thank you!!

adevart · 2023-06-23T23:15:30Z

edit “stable-diffusion-webui/webui-user.sh”

find COMMANDLINE_ARGS variable

Use the following configuration： export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --opt-split-attention --lowvram --no-half --use-cpu all"

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.

mclark4386 · 2023-06-23T23:37:32Z

--opt-split-attention --lowvram --no-half --use-cpu all

What were your command line args, if you don't mind?

adevart · 2023-06-23T23:40:39Z

--opt-split-attention --lowvram --no-half --use-cpu all

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"

NateLevin1 · 2023-06-25T21:36:31Z

This is the correct solution, according to how you are 'supposed' to do it:

Open webui-user.sh.

Replace the line that says:

#export COMMANDLINE_ARGS=""

With:

export COMMANDLINE_ARGS="$COMMANDLINE_ARGS --no-half"

Then everything works great!

maxwwc · 2023-07-24T09:56:47Z

edit “stable-diffusion-webui/webui-user.sh”

find COMMANDLINE_ARGS variable

Use the following configuration： export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --opt-split-attention --lowvram --no-half --use-cpu all"

you help a lot. Thanks.

MacOS 12.6.6, Intel.

AndiDog · 2023-12-22T21:15:23Z

I had NansException and other errors on M1 Pro 32 GB RAM, but upgrading some packages (in virtual environment: pip install --upgrade torch torchvision transformers) helped. That is, use newer versions than installed by webui. SD XL 1.0 base + refiner work that way (txt2img and img2img refinement), while I only got errors before.

Vitkarus added the bug-report Report of a bug, yet to be confirmed label Mar 12, 2023

brkirch mentioned this issue May 8, 2023

Fix MPS on PyTorch 2.0.1, Intel Macs #10201

Merged

akx added the platform:mac Issues that apply to Apple OS X, M1, M2, etc label Jun 13, 2023

remixer-dec mentioned this issue Sep 6, 2023

[Bug]: RuntimeError: "upsample_nearest2d_channels_last" not implemented for 'Half' #12778

Open

1 task

[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

[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

Vitkarus commented Mar 12, 2023

Is there an existing issue for this?

What happened?

Steps to reproduce the problem

What should have happened?

Commit where the problem happens

What platforms do you use to access the UI ?

What browsers do you use to access the UI ?

Command Line Arguments

List of extensions

Console logs

Additional information

Homemaderobot commented Mar 14, 2023 • edited

yuhuihu commented Mar 16, 2023

Scaperista commented Mar 17, 2023

brkirch commented Mar 22, 2023 • edited

Vitkarus commented Mar 25, 2023

Scaperista commented Mar 28, 2023

Awethon commented Mar 29, 2023

imtiger commented Mar 31, 2023

imtiger commented Mar 31, 2023

GoJerry commented Apr 9, 2023

GoJerry commented Apr 9, 2023

hstk30 commented Apr 11, 2023 • edited

FreeBlues commented Apr 11, 2023

hstk30 commented Apr 11, 2023

digital-pers0n commented Apr 20, 2023

ZhelenZ commented Apr 28, 2023

congzai520 commented May 5, 2023

ZXBmmt commented May 7, 2023

oivoodoo commented May 7, 2023 • edited

Vitkarus commented May 7, 2023

iWooda commented May 16, 2023

ctrlaltdylan commented May 19, 2023

huanDreamer commented May 31, 2023

finalcolor commented Jun 3, 2023

iWooda commented Jun 3, 2023

finalcolor commented Jun 3, 2023

finalcolor commented Jun 3, 2023

Muscleape commented Jun 6, 2023

howyeah commented Jun 6, 2023

befriend1314 commented Jun 7, 2023

matto80 commented Jun 9, 2023

adevart commented Jun 23, 2023 • edited

mclark4386 commented Jun 23, 2023

adevart commented Jun 23, 2023

NateLevin1 commented Jun 25, 2023 • edited

maxwwc commented Jul 24, 2023

AndiDog commented Dec 22, 2023

Homemaderobot commented Mar 14, 2023 •

edited

brkirch commented Mar 22, 2023 •

edited

hstk30 commented Apr 11, 2023 •

edited

oivoodoo commented May 7, 2023 •

edited

adevart commented Jun 23, 2023 •

edited

NateLevin1 commented Jun 25, 2023 •

edited