Skip to content
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

terminates on "create model" #451

Closed
realenuf opened this issue Dec 8, 2022 · 7 comments
Closed

terminates on "create model" #451

realenuf opened this issue Dec 8, 2022 · 7 comments
Labels
OOM Issues It's DEEPSPEED, Baby!!

Comments

@realenuf
Copy link

realenuf commented Dec 8, 2022

Python 3.10.6 (main, Nov 2 2022, 18:53:38) [GCC 11.3.0]
Commit hash: 44c46f0ed395967cd3830dd481a2db759fda5b3b
Installing requirements for Web UI

Installing requirements for scikit_learn

#######################################################################################################
Initializing Dreambooth
If submitting an issue on github, please provide the below text for debugging purposes:

Python revision: 3.10.6 (main, Nov 2 2022, 18:53:38) [GCC 11.3.0]
Dreambooth revision: 88cc50a
SD-WebUI revision: 44c46f0ed395967cd3830dd481a2db759fda5b3b

Checking Dreambooth requirements...
[+] bitsandbytes version 0.35.0 installed.
[+] diffusers[torch] version 0.10.0.dev0 installed.
[+] transformers version 4.21.0 installed.
[ ] xformers version 0.0.15.dev0+189828c.d20221207 installed.
[ ] torch version 1.12.1+cu113 installed.
[ ] torchvision version 0.13.1+cu113 installed.
#######################################################################################################

Launching Web UI with arguments:
Dreambooth API layer loaded
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Loading weights [81761151] from /media/iwoolf/BigDrive/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.ckpt
Applying cross attention optimization (Doggettx).
Model loaded.
Loaded a total of 0 textual inversion embeddings.
Embeddings:
Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch().
Loading model from checkpoint.
Loading checkpoint...
v1 model loaded.
Creating scheduler...
Converting unet...
Terminated

Have you read the Readme?
Yes. I can see that the command" pip install torch==1.12.1+cu116 torchvision==0.13.1+cu116 --extra-index-url https://download.pytorch.org/whl/cu116" didn't work, so its still cu113.
I uncommented the lines in webui-user-dreambooth.sh

install command for torch

export TORCH_COMMAND="pip install torch==1.12.1+cu116 torchvision==0.13.1+cu116 --extra-index-url https://download.pytorch.org/whl/cu116"

Have you completely restarted the stable-diffusion-webUI, not just reloaded the UI?
Yes, several times. The program terminates, so I don't even have a choice.
Have you updated Dreambooth to the latest revision?
git pull says its up to date
Have you updated the Stable-Diffusion-WebUI to the latest version?
gut pull says its the latest
No, really. Please save us both some trouble and update the SD-WebUI and Extension and restart before posting this. Reply 'OK' Below to acknowledge that you did this.
OK
Describe the bug
I am following instructions from this video, https://www.youtube.com/watch?v=HahKXY7AQ8c
Which match the instructions in the docs https://github.com/d8ahazard/sd_dreambooth_extension#readme
I select Dreambooth, in "Create Model", I type the name "iwoolf3".
I select the source model v1-5-pruned-emaonly.ckpt, and scheduler ddim.
Then I click on "create".

Provide logs

If a crash has occurred, please provide the entire stack trace from the log, including the last few log messages before the crash occurred.

There's nothing in /var/crash

Environment

What OS?
Ubuntu 22.04.1LTS
If Windows - WSL or native?
not Windows
What GPU are you using?
rtx 3060 12gb

I suspect if I can get help in how to install the correct version of torch with cu116 without conflicts, that this will be fixed.

@realenuf realenuf added the new Just added, you should probably sort this. label Dec 8, 2022
@realenuf realenuf changed the title crashes on "create model" terminates on "create model" Dec 8, 2022
@poondoggle
Copy link

I am also seeing this issue on an install on Ubuntu. I do see this error with each crash:

./webui.sh: line 169: 4138 Killed "${python_cmd}" "${LAUNCH_SCRIPT}" "$@"

The number 4138 is different each time so I presume this is the pid.
It happens with both 1.4 and 1.5 models for me.

@d8ahazard
Copy link
Owner

I think the torch version is a red herring, as it's no longer required to use a specific version.

Please try running with the --ckptfix flag, this will tell the extraction routine to use the CPU only.

@d8ahazard d8ahazard added OOM Issues It's DEEPSPEED, Baby!! and removed new Just added, you should probably sort this. labels Dec 11, 2022
@realenuf
Copy link
Author

xformers has disappeared.

./webui.sh --ckptfix
################################################################
Install script for stable-diffusion + Web UI
Tested on Debian 11 (Bullseye)
################################################################

################################################################
Running on iwoolf user
################################################################

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

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

################################################################
Launching launch.py...
################################################################
Python 3.10.6 (main, Nov 14 2022, 16:10:14) [GCC 11.3.0]
Commit hash: 44c46f0ed395967cd3830dd481a2db759fda5b3b
Installing requirements for Web UI

Installing requirements for scikit_learn

#######################################################################################################
Initializing Dreambooth
If submitting an issue on github, please provide the below text for debugging purposes:

Python revision: 3.10.6 (main, Nov 14 2022, 16:10:14) [GCC 11.3.0]
Dreambooth revision: 88cc50a
SD-WebUI revision: 44c46f0ed395967cd3830dd481a2db759fda5b3b

Checking Dreambooth requirements...
[+] bitsandbytes version 0.35.0 installed.
[!] diffusers[torch] version 0.11.0.dev0 installed.
[+] transformers version 4.21.0 installed.
[!] xformers NOT installed.
[ ] torch version 1.12.1+cu113 installed.
[ ] torchvision version 0.13.1+cu113 installed.
#######################################################################################################

Launching Web UI with arguments: --ckptfix

WARNING:
Need to compile C++ extensions to get sparse attention support. Please run python setup.py build develop
A matching Triton is not available, some optimizations will not be enabled.
Error caught was: No module named 'triton'
Dreambooth API layer loaded
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Terminated

@github-actions
Copy link

This issue is stale because it has been open 5 days with no activity. Remove stale label or comment or this will be closed in 5 days

@github-actions github-actions bot added the Stale label Dec 21, 2022
@realenuf
Copy link
Author

The nvidia driver updated in the last system update, and now I can't log in!

@github-actions github-actions bot removed the Stale label Dec 22, 2022
@d8ahazard
Copy link
Owner

I'd start from scratch, re-install xformers following the official Auto1111 instructions, and ensure you're on the latest version of the extension.

@BrahRah
Copy link

BrahRah commented Jan 26, 2023

I have the same issue with linux mint 21 and the same gpu. I've used a clean install.
My steps are:

-conda create --name automatic python==3.10.6
-conda start automatic
-cd "/home/r2d2/anaconda3/envs/automatic/bin"
-pip install -r "/media/r2d2/4TB/stable-diffusion-webui"/requirements.txt
-pip install open_clip :
ERROR: Could not find a version that satisfies the requirement open_clip (from versions: none)
ERROR: No matching distribution found for open_clip

-pip install open-clip-torch
-pip install clip
-pip install gdown
-pip install xformers==0.0.16rc425

-cd SD dir
-python webui.py --xformers
-install dreambooth from extensions tab (checked if uptodate with git pull)
-give name, select 1.5 mode, select euler-ancestral
-press create model : killed

The log:
https://paste.ofcode.org/6uSCLp9k7JZz8XikKz2qb9

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
OOM Issues It's DEEPSPEED, Baby!!
Projects
None yet
Development

No branches or pull requests

4 participants