Comments (12)
There's this writeup/tutorial here to use windows binaries of these libraries without resorting to WSL:
https://gist.github.com/geocine/e51fcc8511c91e4e3b257a0ebee938d0
maybe something similar can be done for this extension?
from sd_dreambooth_extension.
There's this writeup/tutorial here to use windows binaries of these libraries without resorting to WSL: https://gist.github.com/geocine/e51fcc8511c91e4e3b257a0ebee938d0 maybe something similar can be done for this extension?
Yes, theoretically, this wouldn't be too hard to schlep into the install.py script with a check for the OS. I'll see what time I have to tinker with this today. I don't particularly need 8bit adam, but happy to include it for those that want it.
from sd_dreambooth_extension.
I've now added a bit to the installer that checks if running on windows, and if so, checks for the .dll file specified in the gist. If they're not found, they will be copied to venv, similar to the other script.
from sd_dreambooth_extension.
ok. I'll test this. Last time I did this manually and it couldn't import cudasetup in the cextensions py though.
I'll have to test tomorrow though since it's 2am here
from sd_dreambooth_extension.
I think the dlls only work for pytorch+cu116, and by default you will get pytorch+cu113 when installing webui. Manual upgrading might be required.
I am looking for a way to compile these dlls, but I know nothing about Windows, or marchine learning pipelines or tools in the first place. Can we check if these dlls are safe?
from sd_dreambooth_extension.
I think the dlls only work for pytorch+cu116, and by default you will get pytorch+cu113 when installing webui. Manual upgrading might be required. I am looking for a way to compile these dlls, but I know nothing about Windows, or marchine learning pipelines or tools in the first place. Can we check if these dlls are safe?
I can force it to install specific version of pytorch with the extension - we just need to confirm that updating to cu116 won't break anything else.
from sd_dreambooth_extension.
I think the dlls only work for pytorch+cu116, and by default you will get pytorch+cu113 when installing webui. Manual upgrading might be required. I am looking for a way to compile these dlls, but I know nothing about Windows, or marchine learning pipelines or tools in the first place. Can we check if these dlls are safe?
I can force it to install specific version of pytorch with the extension - we just need to confirm that updating to cu116 won't break anything else.
I did the upgrade and haven't notice anything broken. Further tests needed.
from sd_dreambooth_extension.
But it is still better if we can let the users compile their own versions of these dlls, for any cuda version they have installed.
from sd_dreambooth_extension.
But it is still better if we can let the users compile their own versions of these dlls, for any cuda version they have installed.
Well, the one used natively by SD is cu113, so I think I'd rather precompile and distribute as many versions as possible, then select based on the right CUDA toolkit. Building is probably going to take some backflips, which is why I'm not leaning that way.
from sd_dreambooth_extension.
I'm going to close this and link it up with #7, as they're the same issue.
from sd_dreambooth_extension.
Bitsandbytes was not supported windows before, but my method can support windows.(yuhuang)
1 open folder J:\StableDiffusion\sdwebui,Click the address bar of the folder and enter CMD
or WIN+R, CMD 。enter,cd /d J:\StableDiffusion\sdwebui
2 J:\StableDiffusion\sdwebui\py310\python.exe -m pip uninstall bitsandbytes
3 J:\StableDiffusion\sdwebui\py310\python.exe -m pip uninstall bitsandbytes-windows
4 J:\StableDiffusion\sdwebui\py310\python.exe -m pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl
Replace your SD venv directory file(python.exe Folder) here(J:\StableDiffusion\sdwebui\py310)
from sd_dreambooth_extension.
OR you are Linux distribution (Ubuntu, MacOS, etc.)system ,AND CUDA Version: 11.X.
Bitsandbytes can support ubuntu.(yuhuang)
1 open folder J:\StableDiffusion\sdwebui,Click the address bar of the folder and enter CMD
or WIN+R, CMD 。enter,cd /d J:\StableDiffusion\sdwebui
2 J:\StableDiffusion\sdwebui\py310\python.exe -m pip uninstall bitsandbytes
3 J:\StableDiffusion\sdwebui\py310\python.exe -m pip uninstall bitsandbytes-windows
4 J:\StableDiffusion\sdwebui\py310\python.exe -m pip install https://github.com/TimDettmers/bitsandbytes/releases/download/0.41.0/bitsandbytes-0.41.0-py3-none-any.whl
Replace your SD venv directory file(python.exe Folder) here(J:\StableDiffusion\sdwebui\py310)
from sd_dreambooth_extension.
Related Issues (20)
- [Bug]: Can't create model using trained & generated model using dreambooth. HOT 3
- [Bug]: Exception training model: 'Cannot copy out of meta tensor; no data!'. HOT 2
- [Bug]: HOT 1
- [Bug]: The deprecation tuple ('LoRAAttnProcessor2_0', '0.26.0', 'Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`') should be removed since diffusers' version 0.26.1 is >= 0.26.0 HOT 4
- [Bug]: Completely unable to train any LORA with CUDA out of memory error HOT 2
- RuntimeError: Expected query, key, and value to have the same dtype, but got query.dtype: c10::Half key.dtype: float and value.dtype: float instead. HOT 9
- [Bug]: HOT 1
- [Bug]: OSError: Can't load tokenizer for 'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k'. HOT 2
- [Bug]: TypeError: intercept_args() got an unexpected keyword argument 'multiprocessing_context' HOT 1
- Error al cargar sd_dreambooth_extension en Windows 10: 'LoRAAttnProcessor2_0' no definido HOT 1
- [Bug]: Dreambooth (input tab) not showing correctly HOT 10
- [Bug]: Exception training model: 'type object 'LoraLoaderMixin' has no attribute '_modify_text_encoder''. HOT 4
- [Bug]: AttributeError: 'NoneType' object has no attribute 'unscale_grads' HOT 1
- [Bug]: Unable to further train using previously trained ckpt in dreambooth. HOT 1
- [Bug]: Dreambooth can not start training HOT 3
- AttributeError: module 'jax.random' has no attribute 'KeyArray'[Bug]: HOT 1
- [Bug]: Fast api of concepts don't work HOT 2
- [Bug]: AttributeError: 'NoneType' object has no attribute 'keys' HOT 1
- [Bug]: Unable to do training on sdxl model HOT 4
- [Bug]: Memory Attention default try to use xformers if Class Images Per Instance Image is greather that zero and need to generate images 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 sd_dreambooth_extension.