Comments (4)
It is probably that the 1st version found in the path is still 10.12… because this is what the GUI scripts are seeing. I suspect you might need to fiddle with the path search order and make sure python 3.10.x comes 1st. This is really annoying and bugging me. I wish there was an easy way to specify the version but alas I have not found one that would work reliably.
from kohya_ss.
@srinoom OK... I might have a solution... not sure if it will work for everyone on windows...
Before running setup.bat make sure to delete the existing venv folder. Then try to run:
py -3.10 -m venv venv
Then run setup.bat... does it work?
from kohya_ss.
OK... I actually have implemented it in the dev branch... if you want to try it:
Delete the current venv folder then:
git fetch origin
git checkout dev
git pull
./setup-3.10.bat
from kohya_ss.
Using the python version manager works for me:
git clone https://github.com/pyenv-win/pyenv-win.git "$HOME/.pyenv"
Git bash, add the paths
nano ~/.bashrc
export PYENV="$HOME/.pyenv/pyenv-win"
export PATH="$PYENV/bin:$PYENV/shims:$PATH"
pyenv install 3.10.9
pyenv global 3.10.9
rm -rf venv
/.setup.bat
from kohya_ss.
Related Issues (20)
- Very crazy mistake! When I want to train, it reports an error! I don't know where the problem is! Can you help me? HOT 1
- Confusing sample results when training Lora HOT 4
- Feature Request: if "WANDB run name" empty, use "Trained Model output name" HOT 1
- Lora tab shows no SDXL checkbox--resulting in "Size mismatch" HOT 1
- Presets -- not showing in the toggle down menu after adding to user_presets HOT 4
- dataset repeats is incorrect in wandb -- how do i check?
- Why do the trained LoRA models consistently have a size of 41MB, even when I adjust the number of steps? HOT 2
- Failed to import diffusers.loaders.ip_adapter because of the following error (look up to see its traceback): module 'torch' has no attribute 'compiler'
- Training Fails To Initialise HOT 2
- subprocess.CalledProcessError: Command HOT 1
- Validating ./models/vae existence... FAILURE: not a valid file or folder HOT 1
- feature request: toml filename with model filename + date-time
- ERROR accelerate not found HOT 2
- AttributeError: 'NoneType' object has no attribute 'to'
- how do you turn off TE learning in Lora Module? HOT 5
- Training is constantly failing to start HOT 3
- Lora AdamW8bit Learning Rate seems to have changed HOT 1
- Error message on Paperspace when start training SDXL Lora
- To modify sample prompts during training, edit the prompt.txt file in the samples directory. HOT 1
- [error] - module not found - tk and global_state HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from kohya_ss.