Update README.md
This commit is contained in:
@@ -1,4 +1,4 @@
|
||||
The main node makes your conditioning go towards similar concepts so to enrich your composition or further away so to make it more precise.
|
||||
The main node makes your conditioning go towards similar concepts so to enrich your composition or further away so to make it more precise.
|
||||
|
||||
It gathers similar pre-cond vectors for as long as the cosine similarity score diminishes. If it climbs back it stops. This allows to set a relative direction to similar concepts.
|
||||
|
||||
@@ -57,20 +57,49 @@ Makes the overall intensity of the conditioning to the one of an empty cond. I h
|
||||
If using SDXL the values are worked separately for clip_g and clip_l
|
||||
|
||||
|
||||
# Examples (top row is backward, bottom is forward):
|
||||
# Examples (same seed side by side):
|
||||
|
||||

|
||||
## SD 1.x
|
||||
|
||||

|
||||

|
||||
|
||||

|
||||

|
||||
|
||||
|
||||
|
||||
## SDXL:
|
||||
|
||||

|
||||
|
||||

|
||||
|
||||
_"dark enchanted forest with colorful glowing lights, digital painting, night, black amoled wallpaper, wintery fog, fantasy"
|
||||
_
|
||||

|
||||
|
||||
Too much forward will overreach your general meaning and become more unpredictable:
|
||||
|
||||

|
||||
|
||||

|
||||
|
||||
At 1 it seems to cure the "always the same face" effect:
|
||||
|
||||

|
||||
|
||||
With a lower intensity the effect can still be seen without necessarily changing the composition:
|
||||
|
||||

|
||||
|
||||

|
||||
|
||||
|
||||
## Note:
|
||||
|
||||
I make these nodes to try to understand things deeper. My maths can sometimes be wrong sometimes. Everything I do is self-taught with an overly top-to-bottom approach.
|
||||
|
||||
I feel that what I have done might also be done by tweaking the activation functions but I haven't got that far. Yet.
|
||||
|
||||
Also kittens seems immune to this transformation and inherits little suits before turning into AI chaos.
|
||||
|
||||

|
||||
|
||||
Reference in New Issue
Block a user