[Bug]:

[PedroElFrijol]

Is there an existing issue for this?

• [X] I have searched the existing issues and checked the recent builds/commits

What happened?

Finished all of the installation for the apple silicon instruction but I am running a 2014 Macbook pro intel. In the terminal it stops on this and never does anything else:

"To create a public link, set share=True in launch(). Startup time: 26.8s (import gradio: 2.0s, import ldm: 1.0s, other imports: 1.7s, load scripts: 0.7s, load SD checkpoint: 20.4s, create ui: 0.8s)."

What could be the problem to this?

Steps to reproduce the problem

Follow the instructions for apple silicon and use the sd-v1-4.ckpt model and just run the command ./webui.sh

What should have happened?

This is my first time using this so I do not know what happens after the installation and when I use the command ./webui.sh

Commit where the problem happens

pull request #8503

What platforms do you use to access the UI ?

MacOS

What browsers do you use to access the UI ?

Mozilla Firefox

Command Line Arguments

No

List of extensions

No

Console logs

################################################################
Install script for stable-diffusion + Web UI
Tested on Debian 11 (Bullseye)
################################################################

################################################################
Running on marcelomrios user
################################################################

################################################################
Repo already cloned, using it as install directory
################################################################

################################################################
Create and activate python venv
################################################################

################################################################
Launching launch.py...
################################################################
Python 3.10.10 (main, Feb 16 2023, 03:01:39) [Clang 13.0.0 (clang-1300.0.29.30)]
Commit hash: a9fed7c364061ae6efb37f797b6b522cb3cf7aa2
Installing requirements for Web UI
Launching Web UI with arguments: --upcast-sampling --no-half-vae --use-cpu interrogate
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
==============================================================================
You are running torch 1.12.1.
The program is tested to work with torch 1.13.1.
To reinstall the desired version, run with commandline flag --reinstall-torch.
Beware that this will cause a lot of large files to be downloaded, as well as
there are reports of issues with training tab on the latest version.

Use --skip-version-check commandline argument to disable this check.
==============================================================================
Loading weights [c6bbc15e32] from /Users/marcelomrios/stable-diffusion-webui/models/Stable-diffusion/sd-v1-5-inpainting.ckpt
Creating model from config: /Users/marcelomrios/stable-diffusion-webui/configs/v1-inpainting-inference.yaml
LatentInpaintDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.54 M params.
Applying cross attention optimization (InvokeAI).
Textual inversion embeddings loaded(0): 
Model loaded in 15.1s (load weights from disk: 3.8s, create model: 0.8s, apply weights to model: 6.9s, apply half(): 3.6s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 22.9s (import gradio: 2.2s, import ldm: 1.2s, other imports: 2.2s, load scripts: 0.7s, load SD checkpoint: 15.7s, create ui: 0.7s).

Additional information

No response

[w3cdotorg]

This is not a bug, now you have to load the URL indicated here: Running on local URL: http://127.0.0.1:7860 in your browser.

[PedroElFrijol]

Oh i did not notice that haha thanks! When I start to generate fro a img2img it gives me an error saying:

stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/functional.py", line 2503, in layer_norm RuntimeError: "LayerNormKernelImpl" not implemented for 'Half' RuntimeError: "log" "_vml_cpu" not implemented for 'Half'

[nulqwy]

prob because you followed instructions for apple silicon, however you have intel-based mac, so following linux instructions will have more luck working

[missionfloyd]

If you open webui-user.sh in a text editor and replace #export COMMANDLINE_ARGS="" on line 13 with export COMMANDLINE_ARGS="--autolaunch" it'll open automatically.

[xialei199023]

open webui-user.sh in a text editor and #export COMMANDLINE_ARGS="" with export COMMANDLINE_ARGS="--precision full --no-half --skip-torch-cuda-test". see https://huggingface.co/CompVis/stable-diffusion-v1-4/discussions/64

[PedroElFrijol]

open webui-user.sh in a text editor and #export COMMANDLINE_ARGS="" with export COMMANDLINE_ARGS="--precision full --no-half". see https://huggingface.co/CompVis/stable-diffusion-v1-4/discussions/64

I do this but I get an error that says this:

RuntimeError: Error running command. Command: "/Users/marcelomrios/stable-diffusion-webui/venv/bin/python3.10" -c "import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'" Error code: 1 stdout: stderr: Traceback (most recent call last): File "", line 1, in AssertionError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check

Do I keep it as a comment?

[paulOsinski]

I'm getting the same error message, also on a Silicon Mac M1. I've had a working version of Automatic1111 installed for months, but I updated today with git pull, and I now get this error whenever I try to generate anything.

"RuntimeError: "log" "_vml_cpu" not implemented for 'Half'"

EDIT - updated my OS to Ventura and now there are no issues.