Showing posts with label life on maui. Show all posts
Showing posts with label life on maui. Show all posts

Thursday, June 8, 2023

kandinsky maui big wave

 

Trying some experiments with the new kandinsky synthesis model.



Saturday, April 15, 2023

Tuesday, February 21, 2023

north shore multidiffusion

Experimenting with the new MultiDiffusion SD algorithm.

Thursday, February 9, 2023

Welcome to Paia

 

Someone upgraded the 'welcome to paia' sign at the entry to Paia yesterday.

Friday, January 27, 2023

Saturday, January 21, 2023

Monday, January 16, 2023

Wednesday, January 4, 2023

maui jaws big surf dystopia

 

I started with a photo of big wave surfing at Jaws on Maui's north shore.  I then used the CLIP embedding of that to drive an embedding drift resynthesis above.  I then used that to modulate a generative image synthesis run to make below.


Monday, December 12, 2022

Sunday, December 11, 2022

Saturday, December 10, 2022

Thursday, December 8, 2022

Friday, November 18, 2022

Saturday, November 12, 2022

Thursday, November 10, 2022

north shore view

 


I'm using the hex jitter close pack option for the path start points, and then drawing vector paths off of those.  I'm also using a color palette match for part of the paint coloring derived off of the inverse of the soruce image.

Monday, November 7, 2022

beach synthesis 2

 





Same idea as previous post (CLIP embedding derived from a single Maui beach photo image fed into the latent diffusion model to direct the image synthesis).  I then used Studio Artist processing to create a super flat paint look and build the transition animations.

beach synthesis

 

Generative animation constructed from a series of still images generated using CLIP image embeddings as input to a latent diffusion system (custom model weights for stable diffusion trained by lamba labs).  So no text embedding, just the CLIP image embedding from a painting of a beach scene.

For the second example below i used a real image taken at the beach on Maui's south shore.  That was fed into the CLIP model to generate an embedding that was used to steer the latent diffusion generative image synthesis (no text prompting in the system).



Thursday, October 27, 2022

Monday, October 24, 2022