Update README.md
"it's" to "its"
This commit is contained in:
@@ -7,8 +7,8 @@ NRS seeks to replace the 'naive' linear interpolation of Classifier Free Guidanc
|
||||
[Interactive Graph on Math3D.org](https://www.math3d.org/aTJW4UZtCh)
|
||||
|
||||
### NRS is Applied in Three Steps:
|
||||
1. **Skewing**: The conditioned output tensor is skewed away from the direction of the rejection of the unconditioned tensor on the conditioned tensor. This lengthens the tensor in a direction perpendicular to it's direction without affecting the positive guidance. The tensor is displaced by the rejection x the Displacement parameter.
|
||||
2. **Stretching**: The skewed tensor is stretched towards the direction of the original conditioned tensor based on it's difference from the projection of uncond on cond. 1x stretch adds 100% of this difference to the tensor's length.
|
||||
1. **Skewing**: The conditioned output tensor is skewed away from the direction of the rejection of the unconditioned tensor on the conditioned tensor. This lengthens the tensor in a direction perpendicular to its direction without affecting the positive guidance. The tensor is displaced by the rejection x the Displacement parameter.
|
||||
2. **Stretching**: The skewed tensor is stretched towards the direction of the original conditioned tensor based on its difference from the projection of uncond on cond. 1x stretch adds 100% of this difference to the tensor's length.
|
||||
3. **Squashing**: The skewed and stretched tensor is rescaled towards the original length of the conditioned tensor. 100% squashing outputs the original length of the conditioned tensor simple 'steered' towards the skew & squash output.
|
||||
|
||||
## Parameters
|
||||
|
||||
Reference in New Issue
Block a user