Fooocus mps not supported now on 2.1.66

mps not supported now on 2.1.66

Open vicento opened this issue 8 months ago • 48 comments

Device mps:0 does not support the torch.fft functions used in the FreeU node, switching to CPU. How can i get full MPS support on my silicon mac ?

Oct 15 '23 09:10 vicento

is that showing if you do not use FreeU or you always see this?

Oct 15 '23 09:10 lllyasviel

if i use freeU i get this : Device mps:0 does not support the torch.fft functions used in the FreeU node, switching to CPU. without freeU doesn't see mps error i am on 2.1.675 now

Oct 15 '23 09:10 vicento

macos 14.0 macbookpro m1, 16g ram

[Fooocus Model Management] Moving model(s) has taken 61.51 seconds [Sampler] Fooocus sampler is activated. huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using tokenizers before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) 0%| | 0/30 [00:00<?, ?it/s]/Volumes/1TSSD/AI-project/fooocus/Fooocus/modules/anisotropic.py:132: UserWarning: The operator 'aten::std_mean.correction' is not currently supported on the MPS backend and will fall back to run on the CPU. This may have performance implications. (Triggered internally at /Users/runner/work/pytorch/pytorch/pytorch/aten/src/ATen/mps/MPSFallback.mm:13.) s, m = torch.std_mean(g, dim=(1, 2, 3), keepdim=True) 3%|█▍ | 1/30 [01:40<48:41, 100.73s/it]

Oct 17 '23 12:10 guoreex

App started successful. Use the app with http://127.0.0.1:7860/ or 127.0.0.1:7860 [Parameters] Adaptive CFG = 7 [Parameters] Sharpness = 2 [Parameters] ADM Scale = 1.5 : 0.8 : 0.3 [Parameters] CFG = 7.0 [Parameters] Seed = 4730616638981956459 [Parameters] Sampler = dpmpp_2m_sde_gpu - karras [Parameters] Steps = 30 - 20 [Fooocus] Initializing ... [Fooocus] Loading models ... [Fooocus] Processing prompts ... [Fooocus] Preparing Fooocus text #1 ... [Prompt Expansion] New suffix: intricate, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, unreal engine 5, 8 k, art by artgerm and greg rutkowski and alphonse mucha [Fooocus] Preparing Fooocus text #2 ... [Prompt Expansion] New suffix: extremely detailed, artstation, 8 k, sensual lighting, incredible art, wlop, artgerm [Fooocus] Encoding positive #1 ... [Fooocus] Encoding positive #2 ... [Fooocus] Encoding negative #1 ... [Fooocus] Encoding negative #2 ... Preparation time: 3.79 seconds [Sampler] refiner_swap_method = joint [Sampler] sigma_min = 0.02916753850877285, sigma_max = 14.614643096923828 Requested to load SDXL Loading 1 new model [Fooocus Model Management] Moving model(s) has taken 60.01 seconds [Sampler] Fooocus sampler is activated. 0%| | 0/30 [00:00<?, ?it/s]/Applications/Fooocus/modules/anisotropic.py:132: UserWarning: The operator 'aten::std_mean.correction' is not currently supported on the MPS backend and will fall back to run on the CPU. This may have performance implications. (Triggered internally at /Users/runner/work/pytorch/pytorch/pytorch/aten/src/ATen/mps/MPSFallback.mm:13.) s, m = torch.std_mean(g, dim=(1, 2, 3), keepdim=True) 7%|██▋ | 2/30 [04:50<1:07:49, 145.34s/it] User stopped Total time: 355.80 seconds

Oct 24 '23 13:10 Gitterman69

if i use freeU i get this : Device mps:0 does not support the torch.fft functions used in the FreeU node, switching to CPU. without freeU doesn't see mps error i am on 2.1.675 now

same here :( i want to use fooocus on my macbook m1 so bad :)

Oct 25 '23 11:10 Gitterman69

yes - this is so sad :( @lllyasviel heeeeeeeeeelp

Oct 26 '23 20:10 Gitterman69

bump

Oct 28 '23 11:10 Gitterman69

Pay attention to the same problem

Oct 28 '23 15:10 tiancool

bump

Nov 05 '23 06:11 Gitterman69

same.

Nov 14 '23 04:11 none2serious

Same here, Fooocus v2.1.8241 Looks like Pytorch has added support: https://github.com/pytorch/pytorch/pull/110829

Nov 29 '23 22:11 waterydan

bump

Nov 30 '23 14:11 robpal

bump

Nov 30 '23 15:11 Tygrha

[Fooocus] Encoding positive #1 ... [Fooocus] Encoding positive #2 ... [Fooocus] Encoding negative #1 ... [Fooocus] Encoding negative #2 ... [Parameters] Denoising Strength = 1.0 [Parameters] Initial Latent shape: Image Space (1152, 896) Preparation time: 20.42 seconds [Sampler] refiner_swap_method = joint [Sampler] sigma_min = 0.0291671771556139, sigma_max = 14.614643096923828 Requested to load SDXL Loading 1 new model [Fooocus Model Management] Moving model(s) has taken 113.59 seconds huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using tokenizers before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) 0%| | 0/30 [00:00<?, ?it/s]/Users/ty/Desktop/Fooocus-main/modules/anisotropic.py:132: UserWarning: The operator 'aten::std_mean.correction' is not currently supported on the MPS backend and will fall back to run on the CPU. This may have performance implications. (Triggered internally at /Users/runner/work/pytorch/pytorch/pytorch/aten/src/ATen/mps/MPSFallback.mm:13.) s, m = torch.std_mean(g, dim=(1, 2, 3), keepdim=True) 7%|██████ | 2/30 [06:31<1:30:11, 193.25s/it]

Nov 30 '23 16:11 Tygrha

The operator 'aten::std_mean.correction' is not currently supported on the MPS backend and will fall back to run on the CPU

The same error

193.25s/it

The same speed

Bump

Nov 30 '23 16:11 ambraxia

If my understanding is correct, it looks like a compatibility issue with pytorch and apple silicon.

Does anyone know if there is a way to adjust the parameters in Fooocus to avoid using the 'aten:std_mean.coorection', but rather some other calculation that would be supported?

Nov 30 '23 19:11 Tygrha

Bump, I'd love to get an update on that.

Dec 01 '23 16:12 dch09

any update?

Dec 01 '23 23:12 emilmammadov

any update?

Dec 02 '23 01:12 muratdemirkiran33

bumpedy bump bump - can we haz some mac arm love plz

Dec 02 '23 01:12 Gitterman69

UserWarning: The operator 'aten::std_mean.correction' is not currently supported on the MPS backend and will fall back to run on the CPU. This may have performance implications. (Triggered internally at /Users/runner/work/_temp/anaconda/conda-bld/pytorch_1701416305940/work/aten/src/ATen/mps/MPSFallback.mm:13.) s, m = torch.std_mean(g, dim=(1, 2, 3), keepdim=True)

Dec 02 '23 09:12 gregplumbly

same here

Dec 04 '23 09:12 Kolch

Same on Intel iMac 2020 with AMD Graphics?

Dec 04 '23 21:12 BoomerCorp

Macbook M3 Pro suffers from the same problem - So i guess the whole lineup of Apples Silicon CPU's is affected

Dec 05 '23 10:12 winnduu

Same on MacBook Pro Apple M2 Pro, macOS Sonoma Version 14.1.

... UserWarning: The operator 'aten::std_mean.correction' is not currently supported on the MPS backend and will fall back to run on the CPU. This may have performance implications. (Triggered internally at /Users/runner/work/pytorch/pytorch/pytorch/aten/src/ATen/mps/MPSFallback.mm:13.) ...

Dec 07 '23 17:12 amediantsev

Same issue! Bump

Dec 11 '23 17:12 bhardwajshash

Same

Dec 18 '23 20:12 semyonf

same

Dec 20 '23 12:12 oscody

same M2 Pro, Fooocus version: 2.1.854

Dec 21 '23 19:12 Dkray

bump for visibility!

Sent from Proton Mail for iOS

On Thu, Dec 21, 2023 at 20:58, Dkray @.***(mailto:On Thu, Dec 21, 2023 at 20:58, Dkray < wrote:

same M2 Pro, Fooocus version: 2.1.854

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>

Dec 21 '23 22:12 Gitterman69

Fooocus Fooocus copied to clipboard

mps not supported now on 2.1.66

Fooocus
Fooocus copied to clipboard