A depository for John Dalton's personal artwork. Studio Artist, MSG, procedural art, WMF, digital painting, image processing, human vision, digital art, slit scan, photo mosaic, artistic software, video effects, computer painting, fractals, generative drawing, paint animation, halftoning, video effects, photo manipulation, modular visual synthesis, auto-rotoscoping, directed evolution, computational creativity, artificial intelligence, generative ai, style transfer, latent diffusion
Friday, November 4, 2022
Thursday, November 3, 2022
Wednesday, November 2, 2022
hot malasada
Generative image synthesis animation exploration of the song titles of the WMF cd Hot Malasada. The same story line text prompt key-framing for all of these. The variation in the imagery across the different animations (as well as the flow while in specific keyframe sections) comes from how you modulate the underlying generative system.
Here's a way to think about it. The normal random U-Net latent initialization for the latent diffusion has very specific statistical properties that are very restricted compared to what they potentially could be. So if you break out of that box and try to utilize all of the potential range of that starting point U-Net latent representation you have a much bigger (and usually much more visually interesting) generative design space to work with.
Labels:
animation,
generative ai context,
latent diffusion,
wmf
Tuesday, November 1, 2022
bargaintown 2
Continued exploration of multi-modal generative animations created using the song titles from the WMF cd Bargaintown as the story line text prompting keyframes.
bargaintown
The storyline text prompting keyframes for the generative animation comes from the song titles in the WMF cd Bargaintown. Trying to balance out the style prompting between the cds references to life in Honolulu on Oahu and the more abstract song specific mood references.
Subscribe to:
Posts (Atom)





















