Comments (5)
Can you provide your 26 training images so we can reproduce? You can black them out or blur them or whatever, just keep the names the same.
These widgets are finicky, and other people have been reporting a few issues with them as well.
from dreambooth-stable-diffusion.
Looks like the ipwidget FileUpload can only do up to 10mb max (which is incredibly stupid lol).
We have a couple work arounds
- Upload 1 image and proceed as normal. After the config is generated all you have to do is upload your remaining training images to the training_images folder.
- Compress your input images to stay under the 10mb file limit by using jpegs. You shouldn't notice any quality loss.
from dreambooth-stable-diffusion.
Hey @djbielejeski,
Thanks for the prompt response.
I've attached the training images to this message. Hopefully this helps. I was still able to get my training done through the legacy dreambooth file, but hopefully I get to do my training on the new dreambooth file soon, as it's so much more user-friendly.
Thanks!
Link removed by author.
from dreambooth-stable-diffusion.
@djbielejeski Thank you so much for the prompt assistance! Now that you mention it, my PNG-s are wildly uncompressed.
It'd be nice to have a little file size indicator or better error message, but at least I can work around the limitation now that I know the cause. I'll go with your suggestions.
Thanks a ton once again!
from dreambooth-stable-diffusion.
Idk if it helps, but i always put my pngs on BIRME, this will compress and resize the files for you.
Hope it helps.
https://www.birme.net/?target_width=512&target_height=512
from dreambooth-stable-diffusion.
Related Issues (20)
- NameError: name 'trainer' is not defined HOT 8
- Does dreambooth support multi-subjects training? HOT 12
- Training on a model other than SD 1.5 HOT 6
- Regularization step always stops almost at the end HOT 1
- Conda OOM issue locally HOT 1
- Upload Images in Dreambooth Training Environment Setup fails on dreambooth_joepenna.ipynb HOT 4
- num_samples should be a positive integer value, but got num_samples=0 HOT 1
- Establish a baseline with a sample set of training images HOT 1
- Ubuntu Running Error HOT 9
- ImportError: cannot import name '_PATH' from 'pytorch_lightning.utilities.types'
- support freezing text_encoder layers for OpenCLIP
- how to train x4-upscaling? HOT 1
- OutOfMemoryError: CUDA out of memory (WHY?) HOT 2
- Failure in installation step 2: ERROR: file:///content does not appear to be a Python project: neither 'setup.py' nor 'pyproject.toml' found. HOT 2
- pickle.UnpicklingError: invalid load key - Issue Using Safetensor training model HOT 1
- Torch Install Failure: "raise AssertionError("Torch not compiled with CUDA enabled") AssertionError: Torch not compiled with CUDA enabled" HOT 1
- Where is PPL implemented
- Error: HeaderTooLarge HOT 4
- Does this program support training based on muti-GPUS ?
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 dreambooth-stable-diffusion.