-
Notifications
You must be signed in to change notification settings - Fork 5
Model Training ‐ Comparison ‐ [Noise Offset]
Models | Logs | Graphs | Configs
Noise Offset
(NO
) allows you to add additional noise to the training images, theoretically making the generated images more contrasted and vivid.
Compared values:
-
0.00
-BD
, -
0.05
, -
0.10
, -
0.15
.
DLR(step)
It's indeed strange that the DLR
slightly decreases with increasing NO
for GR = 1.02
, while for GR = ∞
, it skyrockets.
Loss(epoch)
And the loss
increases in all the cases except for 0.05
, which is often recommended to use. However, for GR = ∞
and NO = 0.15
, something very creepy seems to happen.
Finally, we have a clear example of an overtrained model with noticeable artifacts :)
Actually, the image periodically becomes more vivid and contrasted. However, in the case of GR = 1.02
with NO = 0.10
and NO = 0.15
, the similarity with the character seriously deteriorates, and the colors can become significantly washed out. But now we finally understand what the GR
restriction protects us from :) In the case of GR = ∞
, good results are achieved with both NO = 0.05
and NO = 0.10
, but in the latter case, the initial epochs are terrible, and something of quality is obtained only towards the end of training.
I would say it's safer to use the default value of 0.00
, but for the sake of experimentation, you can try 0.05
. It's also worth mentioning that SDXL
model has been trained with 0.0357
and it could be good choice too. Beyond that, various issues start to arise.
- Introduction
- Examples
- Dataset Preparation
- Model Training ‐ Introduction
- Model Training ‐ Basics
- Model Training ‐ Comparison - Introduction
Short Way
Long Way
- Model Training ‐ Comparison - [Growth Rate]
- Model Training ‐ Comparison - [Betas]
- Model Training ‐ Comparison - [Weight Decay]
- Model Training ‐ Comparison - [Bias Correction]
- Model Training ‐ Comparison - [Decouple]
- Model Training ‐ Comparison - [Epochs x Repeats]
- Model Training ‐ Comparison - [Resolution]
- Model Training ‐ Comparison - [Aspect Ratio]
- Model Training ‐ Comparison - [Batch Size]
- Model Training ‐ Comparison - [Network Rank]
- Model Training ‐ Comparison - [Network Alpha]
- Model Training ‐ Comparison - [Total Steps]
- Model Training ‐ Comparison - [Scheduler]
- Model Training ‐ Comparison - [Noise Offset]
- Model Training ‐ Comparison - [Min SNR Gamma]
- Model Training ‐ Comparison - [Clip Skip]
- Model Training ‐ Comparison - [Precision]
- Model Training ‐ Comparison - [Number of CPU Threads per Core]
- Model Training ‐ Comparison - [Checkpoint]
- Model Training ‐ Comparison - [Regularisation]
- Model Training ‐ Comparison - [Optimizer]