Comments (4)
Try installing the bitsandbytes optional version:
from kohya_ss.
from kohya_ss.
I updated to the latest version today, the torch version change did not work to well tho. When launching kohya, it noticed the version was to old but failed updating. Nevermind, got it working by manually installing requirements using pip install.
Afterwards bitsandbytes was the issue, it wanted to get cuda files, but couldn't find them in my cuda 12.1 toolkit. Found a fix in an older post, which was to download and install a pre-compiled bitsandbytes.
This one worked for me, it is the currently used version as wel:
I called activate.bat in venv, used pip uninstall bitsandbytes and pip install this file instead, now works without issues.
from kohya_ss.
Yeah… the current setup of the gui expect the 11.8 toolkit… there is no easy way of making this work for everyone I am afraid.
from kohya_ss.
Related Issues (20)
- Debiased Noise Estimation for Dreambooth
- training support for cascade HOT 4
- returned non-zero exit status 1. HOT 17
- Error extracting LyCORIS HOT 4
- Merge LoRAs outputs a non existant 'corrupt safetensor Lora merger file' HOT 4
- Configs File's are no longer loading in Version: v22.6.2 HOT 2
- --lora_network_weights not being recognized as a valid argument HOT 6
- safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer HOT 2
- kohya Lora trainer can't find base XL model HOT 7
- [Feature request] Create json file for training from Lora-Metadata? HOT 1
- Stable-cascade support HOT 27
- Lora Training doesn`t work anymore and i am to much of a Jerry to understand why, Pls Help HOT 6
- batch["images"] == None after caching latents, but I want to use it. HOT 2
- NaN’s loras weight HOT 1
- Struggling with SDXL LoRA training
- Is it possible to update the lycoris related files under Tools? HOT 4
- [Feature request] Option to auto generate regularization images for training data set HOT 1
- ValueError when changing Model Quick Pick from SD V1.5 to SD XL 1.0 in LoRA training
- Need to update validation of LR with DAdaptation optimizer
- learning_rate_te2 must be given as 0 HOT 6
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.