new years eve embedding drifter

 

new beginnings drift

 

a new beginning

 

Vectorized resynthesis of the previous post smart tesselate image (first one).  The resynthesis is based on generating a CLIP image embedding and then 'pushing' it with a text embedding and then using the pushed image embedding for direct image to image resynthesis.  If you just tried to work with that text embedding in conventional direct text to image synthesis you always get things that look like the representative image shown below.  You will never get any of the new visually interesting things you get when you work with manipulating the image embeddings in a resynthesis approach.  By visually interesting i mean things that aren't representative stereotypes of the images used in the original model training set.

Smart Tesselate

Experimenting with the new Smart Tesselate technique option in the pre_V6 Vectorizer.

Rebirth

 

RGA Effect Smart Clip 2

 

Still tweaking the interaction of the RGA Effect and the SmartClip computation in the Vectorizer.  Also adding some new options to SmartClip.

flat region colorize experiments 3

 

flat region colorize experiments 2

 

flat region colorize experiments

 

H-N-Y

 

RGA Effect Smart Clip

 

The RGA Effect works with the SmartClip options in the Vectorizer now in pre_V6.  So i'm using DualLumThreshold for SmartClip with a Poly Simplify2 RGA Effect in the Tesselate generator.  The RGA EFX would not effect the SmartClip part of it before.

breakout

 

celebration

 

embedding drift 2

 

Second experiment using the negative Loab prompt from the wikipedia article to push the resynthesis embedding over iterative drift resynthesis cycles.  Loab's granddaughter?

embedding drift

 

Tried a negative embedding drift based on the info in the Loab wikipedia article.  I found something more horrifying than Loab at the end, ha,ha.

Loab

 

Resynthesis of an image of 'Loab', which this sciencealert article describes as 'a nightmare face haunting ai art'.  Loab even has its own wikipedia page.  Urban myth?  Ai art trolling?  Real phenomena?

I tried an 'image to text' synthesis approach and generated the following text off of the Loab image used in the article.  Same image i used as the one-shot seed for generating above via image to image resynthesis.

"the woman just she their the woman she completely not having just her girl all her real <unk> some women have <unk> and she

several women very shocked her life like she just had a lot of fun around a giant mushroom giant woman and her little daughter

she almost died child who made famous was shocked at her death so very angry she <unk> joke and smiling at dead lady with ear

a woman with a child who's almost to hurt her mother had her ugly face, <unk> who she was dressed in a hospital"

I then ran a few iterations of a resynthesis embedding drift on the original Loab image and got the image below.

meg-a-tron resynthesis

 

meg-a-tron

 

Odds and Sods 3

 

Tess-A-lations Resynthesis

 

Tess-A-lations

 

Bloc Headz

 

resynthesis excursion 2