The Generative Token is obtained in two stages: in the first stage warped noise is generated using the method explained by Inigo Quilez (see Licence.txt for reference); in the second stage, using Sobel method for edge detection, the noise gradient orientation is used to generate flow lines for the “Fur”.
The first stage generate an image colored using the values of warped noise.
The second stage generate another image using gradient orientations both for shapes (the fur) and for coloring.
The two images are blended together to obtain the final result.
In both stages color-map can be a precalculated palette or a generated one. There are four precalculated palettes read from files and many more generated with random phases.
The user can save a 1200×1200 png with ‘s’.
Sources of variations are:
– Four noise warping control parameters generating different grade of complexity and different shape
– One flattening control parameter
– Blending of the two intermediate images
– precalculated (four) or generated (many) color mapping for warped noise
– precalculated (four) or generated (many) color mapping for flow furry lines
Features:
– Color Palette: the kind of color palette used in the two stages, (Gen + Gen | Gen + Map | Map + Gen | Map + Map)
– ColorGen: the color scheme for generated palette, can be “Grays” (one) or “Colors” (many)
– ColorMap: the precalculated color palette (the name)
– NoiseControl: noise control parameter, 0 – 15
– FlatControl: flattening control parameter, 1 – 19
– Rare: when “Color Palette” = “Gen + Gen” and “ColorGen” = “Grays”, each event has 25% probability so should be 6.25%