unthinking
photography

Rosa Menkman asks 'what kind of accuracy will be necessary and what software or hardware will render the image?'

A team of researchers pursue an intuitive prompt-to-prompt editing framework, where image edits are controlled by text only.

Reconstructing realistic images with high semantic fidelity is still a challenging problem. Let's try with a latent diffusion model.

These photos have been manipulated in a process of selectively re-imagining male-coded parts in the artist's appearance within the images using a commonly available out-painting text-to-image AI tool.

Reconstructing 3D human shape and pose from a monocular image Reconstructing 3D human shape and pose from a monocular image is challenging despite the promising results achieved by the most recent …

“I noticed a structural abnormality when looking at a hex dump of an image file from an unknown origin only to discover it contained what I now understand is an IPTC special instruction. Shocking …

Jeffrey Thompson, Every Possible Photograph, 2013 Though limited to eight colors at a very low resolution, the piece will take approximately …

algopop: Maria Callas - Style Transfer by Lulu xXX Paris-based CGI artist Lulu xXX has been experimenting with style transfer, and has made one of the more beautiful videos I’ve seen using this …