Comments (6)
I also connot click the "..." button after prompt source button.
from onetrainer.
Ok. After enable latent caching. This error disappeared. But another happened...
from onetrainer.
For the last error: you disabled text encoder and unet training. You need to enable at least one. Rwgarding the first error, I can add a few more validations and better error messages. But without knowing the data set, I can't tell you what the problem is.
from onetrainer.
For the last error: you disabled text encoder and unet training. You need to enable at least one. Rwgarding the first error, I can add a few more validations and better error messages. But without knowing the data set, I can't tell you what the problem is.
I figured out that the error was caused by the latent caching. After enable it, the error disappeared. The reason I might think about is I only created one concept with a folder but training epochs is set to 100 which is bigger than 1 concept object.
from onetrainer.
No. You didn't do anything wrong. This is a bug inthe code. It's already fixed in the ema branch, just not merged to master yet. I will do that later today. Then it will be possible to disable latent caching again
from onetrainer.
No. You didn't do anything wrong. This is a bug in the code. It's already fixed in the ema branch, just not merged to master yet. I will do that later today. Then it will be possible to disable latent caching again
Thanks! Then I will wait for the version to see how it works!
Issue closed.
from onetrainer.
Related Issues (20)
- Where to put training data directory HOT 1
- KeyError: 'tokens_1' while training sdxl HOT 2
- Error during sampling HOT 3
- RuntimeError: "grid_sampler_2d_cuda" not implemented for 'BFloat16' HOT 1
- Can't finetune sdxl with a 4090, out of memory HOT 12
- queue system? HOT 1
- Error when training embedding on SDXL 1.0 HOT 1
- Issues with VAE Finetuning HOT 3
- resizing UI window
- option to disable gradient checkpointing HOT 1
- Is it compatible with linux? HOT 7
- Any way to set optimizer arguments? HOT 1
- Tutorials? HOT 5
- Bitsandbytes error on launch HOT 1
- SDXL: lora_te2_text_projection is not found in created LoRA modules. HOT 5
- Issue with sampling HOT 3
- bug report after updating to the latest version
- Lora training fails with latest update despite having alignprop disabled via UI/train.sh HOT 2
- Error when 'Normalize Masked Area Loss' option is toggled on while 'Masked Training' is turned off
- Is there any threshold to the limit the tokens? 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 onetrainer.