[Bug]: Segmentation fault

[LIN-ALOHA]

Is there an existing issue for this?

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

What happened?

python launch.py

Python 3.10.11 | packaged by conda-forge | (main, May 10 2023, 18:58:44) [GCC 11.3.0] Version: v1.2.1 Commit hash: 89f9faa63388756314e8a1d96cf86bf5e0663045 Installing requirements Launching Web UI with arguments: Segmentation fault

Steps to reproduce the problem

1. Go to ....
2. Press ....
3. ...

What should have happened?

webui should proceed correctly after executing launch.py.

Commit where the problem happens

89f9faa63388756314e8a1d96cf86bf5e0663045

What platforms do you use to access the UI ?

No response

What browsers do you use to access the UI ?

No response

Command Line Arguments

python launch.py

List of extensions

No

Console logs

(webui) xxx@task-20230512150124-91891:/xxx/stable-diffusion-webui$ python launch.py 
Python 3.10.11 | packaged by conda-forge | (main, May 10 2023, 18:58:44) [GCC 11.3.0]
Version: v1.2.1
Commit hash: 89f9faa63388756314e8a1d96cf86bf5e0663045
Installing requirements
Launching Web UI with arguments: 
Segmentation fault

Additional information

No response

[jp-berg]

Maybe slightly different issue:

Python 3.10.6 (main, Mar 10 2023, 10:55:28) [GCC 11.3.0]
Version: v1.2.1
Commit hash: 89f9faa63388756314e8a1d96cf86bf5e0663045
Installing requirements
Launching Web UI with arguments: 
No module 'xformers'. Proceeding without it.
Loading weights [6ce0161689] from /home/pc/ML/StableDiffusion/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 3.7s (import torch: 0.7s, import gradio: 0.7s, import ldm: 1.3s, other imports: 0.3s, load scripts: 0.2s, create ui: 0.3s).
Creating model from config: /home/pc/ML/StableDiffusion/stable-diffusion-webui/configs/v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying cross attention optimization (Doggettx).
Segmentation fault (core dumped)

OS: Kubuntu 22.04.2 LTS x86_64 Kernel: 5.15.0-72-generic GPU: AMD ATI Radeon RX 6700 XT ROCm: 5.4.2

[ChrisAi89]

Same issue as @ jp-berg c

[Syndromekwk]

Same issue as jp-berg

`root@Omnidroid:/dockerx/stable-diffusion-webui# REQS_FILE='requirements.txt' python launch.py Python 3.8.16 (default, Mar 2 2023, 03:21:46) [GCC 11.2.0] Version: v1.3.2 Commit hash: baf6946e06249c5af9851c60171692c44ef633e0 Installing requirements Launching Web UI with arguments: No module 'xformers'. Proceeding without it. Loading weights [6ce0161689] from /dockerx/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors Creating model from config: /dockerx/stable-diffusion-webui/configs/v1-inference.yaml LatentDiffusion: Running in eps-prediction mode DiffusionWrapper has 859.52 M params. Downloading (…)olve/main/vocab.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 961k/961k [00:00<00:00, 14.1MB/s] Downloading (…)olve/main/merges.txt: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 525k/525k [00:00<00:00, 98.0MB/s] Downloading (…)cial_tokens_map.json: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 389/389 [00:00<00:00, 476kB/s] Downloading (…)okenizer_config.json: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 905/905 [00:00<00:00, 1.09MB/s] Downloading (…)lve/main/config.json: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4.52k/4.52k [00:00<00:00, 1.13MB/s] Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). Startup time: 5.1s (import torch: 0.8s, import gradio: 0.8s, import ldm: 0.3s, other imports: 0.3s, load scripts: 0.3s, create ui: 0.3s, gradio launch: 2.2s). Applying optimization: Doggettx... done. Segmentation fault (core dumped)`

Ubuntu 22.04 5.19.0-43-generic AMD ATI Radeon RX 6700 XT Docker Container rocm/pytorch latest

[inferenceus]

Same issue is occuring for me. ROCm installed, pip installed, torch2.0.1+rocm5.4.2 installed, OS updated, segmentation fault when running webui.sh after it loads weights and mentions Doggettx in the start-up sequence.

Running stable-diffusion-webui v1.3.2 natively using COMMANDLINE_ARGS:"--skip-torch-cuda-test --precision autocast --no-half-vae --listen 7860 --theme dark"

OS: Gentoo Linux Kernel: 6.1.34 GPU: AMD Radeon RX 6700 XT

[a73s]

Im having this same issue in the docker container. 6700xt

[Vendaciousness]

I'm also having this issue randomly while running Deforum jobs. I notice the OP is running a later version of Python than is recommended by WebUI. And so am I (3.10.12), since that's the one that installed automatically in Linux Mint Cinnamon.

Could this be the problem? I'm going to try downgrading to the version I've always used on Windows, 3.10.9 and see if it fixes the problem. I'll check back in if it does.