A challenge for “neural pictures” is the amount of memory required for rendering even a small photo-like picture. Applying the largest GPUs and TPUs available at Google still may only produce a 2K image.
An alternative approach is to use vector graphics, that is, images not defined as easily-managed rows of pixels but as abstract lines and curves and fillable regions, as in software like Adobe Illustrator, inkScape, or formats like path-based SVGs. A sharp-edged circle renders as a sharp-edged circle regardless of the final print or JPG size.
Which is what I’ve been doing, and what this post is about.
Paintings from See See’s studio are now available via Petaluma’s Riverfront Gallery.
More CLIP-Guided VQGAN. I like that it can guess at how to draw things that might not exist in nature: in this case, a 19-century textbook illustration about drying octopus bones on the shore at Marseille.
Been away for a few weeks: in the meanwhile, my computers have been happily synthesizing.