You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+22-2Lines changed: 22 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -12,8 +12,28 @@ Adds math nodes for numbers and types which do not need it. I got inspired by wa
12
12
13
13
# Features
14
14
15
-
- expression parsing with support for functions (sin, cos, tan, asin, acos, atan, atan2, sinh, cosh, tanh, asinh, acosh, atanh, abs, sqrt, ln, log, exp, pow, smin, tmin, smax, tmax, tnorm,snorm (norm not applicable on number math node), floor, ceil, round, gamma,clamp,sigmoid), math operators (binary and unary +,- and ^,*,/,%) and constants (e,pi)
16
-
- run expressions on both components of CONDITIONING (not that I know what they do), LATENT, IMAGE and FLOAT
15
+
- expression parsing with support for functions and variables:
16
+
- functions:
17
+
- sin, cos, tan
18
+
- asin, acos, atan
19
+
- atan2 (x,y)
20
+
- sinh, cosh, tanh (can produce NaN outside range -1...1)
21
+
- asinh, acosh, atanh (can produce NaN outside range -1...1)
22
+
- abs, sqrt (produces NaN on negative numbers), ln (log with base e), log (base 10), exp, pow
23
+
- smin, tmin, smax, tmax, tnorm,snorm (norm not applicable on number math node), floor, ceil, round, gamma,clamp,sigm, math operators (binary and unary +,- and ^,*,/,%) and constants (e,pi)
24
+
- s prefixed return one number
25
+
- t prefixed work element-wise
26
+
- variables
27
+
- a, b, c, d : inputs of type based on node
28
+
- w, x, y, z : each node allows use of 4 additional floats
29
+
- W : Width of tensor - does not work on FLOAT and CONDITIONING
30
+
- H : Height of tensor - does not work on FLOAT and CONDITIONING
31
+
- C : Channel of tensor - used as color chanel in IMAGE or as information channel in others. does not work on FLOAT and CONDITIONING
32
+
- B : Batch - does not work on FLOAT and CONDITIONING
33
+
- X : X position in tensor - does not work on FLOAT and CONDITIONING
34
+
- Y : Y position in tensor - does not work on FLOAT and CONDITIONING
35
+
- I : Tensor used to initalise sampler - usually zeroed out and generated by Empty Latent Image node - Exclusive for NOISE
36
+
- run expressions on both components of CONDITIONING (not that I know what they do), LATENT, IMAGE, NOISE and FLOAT
0 commit comments