changing tides

 

after the flood

 

Playing around with the new DeepFloyd non-latent Imagen-like generative synthesis model.

vitrous spirit

 

Added some new path tracking options in fixed color control panel of paint synthesizer.  Working with the new min-max fixed color options here and the fixed color computation is setup to only occur at the beginning of generative multi-pen auto paths.

butterfly journey

 

a walk on the wild side 3

 

a walk on the wild side 2

 

a walk on the wild side

 

oblique dazzle promenade

 

oblique camouflage

 

the anticipation journey 2

 

cold front big swell

 

Finally got a version of the new convolutional generative model going for tests.  This model is based on Muse style latent masking as opposed to diffusion.

the roadway to progression

 

the anticipation journey

 

no dominion

 

Added a random Ip Op black and white hard contrast EFX technique option to Gallery Show in response to Otto's Studio Artist user forum question.  I'm auto-colorizing the output using the gallery Show End Cycle processing.

genesis of a new beginning

Der Struwwelpeter Forest Journey

 

representation dodger

 

old town

 

road work

 

Playing around with the Paella generative model, which is just a conv net as opposed to transformer driven diffusion like most of the others.  Super fast due to the simplicity of the architecture.

north shore vog daze

 

fear is a man's best friend

 

easy street

 

reality paradox

 

texas t-bone

 

dazzle inner sanctum

 

CLIP Integrator Dazzler

 

Roundabout resynthesis approach using CLIP Integrator to go from an image input to a long algorithmically generated text prompt that then gets input to stable diffusion 2.0 to generate resynthesized generative image output.  Not as good as the more straightforward direct input image embedding resynthesis i normally work with, but better than i thought it would be for the particular input image i used for the experiment.

pattern boxer

 

Dazzler