Comments (4)
After restarting the gui and reloading the webpage, it should appear at the bottom of the list.
I copied the json file directly into user_presets without any editing.
from kohya_ss.
thanks it did work. for some reasons my json files didnt have extension when i downloaded from runpod. seems to be a weird glitch. now showing fine on preset toggle. thanks again
from kohya_ss.
:-)
from kohya_ss.
@b-fission just a weird question. My usual Learning rate for Lora module SDXL adamw8bit training was always 1e-4 with xformers. I recently started using sdpa. Worked fine in Finetune module. But in lora, its outputting garbled samples. I am setting TE learning at 1/10th the lr of unet.
Am i missing something?
UPDATE: oh wait. I think i was training in cli with instead sdxl_train.py isntead of sdxl_train_network.py
from kohya_ss.
Related Issues (20)
- unable to train sdxl lora using runpod training stops without throwing error HOT 2
- pip install argument might be passed incorrectly HOT 2
- latent cache error RuntimeError: NaN detected in latents
- missing options in Dreambooth training HOT 17
- The second GPU can't be used
- getting an error for using optimizer
- Textual Inversion Broken | SDXL not training at all, SD1.5 other error HOT 7
- 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
- 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 1
- 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
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.