The DKNY MVFW experience and an ode to New York

You (yes you) attended the bastardous exhibition of berk aka princess camel aka guerrilla pimp minion bastard at Sovpunk Museum. Let there be more glitch in your life!

In 2021, a small collection of about 20 Alt Punks were dropped into the OpenSea. They were a group of punks, wearing appropriate attire for fast food workers. They were the embodiment of the Bear Market Fast Food Meme... The Fast Food Punks had been born. During many weeks of late nights and long weekends each Fast Food Punk was made individually by hand by the artist named NFT4Life. The artist uploaded and minted to OpenSea. There must have been an easier way to do this, but the creator of the Fast Food Punks was new to the NFT space and just jumped in using the apps he was familiar with to make the FFP's. The Fast Food Punks were made to be affordable for everyone and thus were listed at 0.01ETH in the primary market. Over the next couple of months all 1,000 Fast Food Punks were individually created and uploaded individually 'by hand' and minted in a number of large and smaller stealth drops. Then they started selling on the secondary market... and the rest is history. The ethos of the Fast Food Punks is to enjoy life, keep things light and most of all - have fun.

Almost a year ago, Berk created an immersive NFT collection with each image (or BGAN as some call them) generated via a GAN network. This was one of the very first instances of an AI generated NFT. Most of the BGANs have a solid background, but about 1/5th have a patterned background. An even smaller subset of are actually morphing gifs. There has recently been a growing trend to integrate PFP NFT’s [Profile Picture NFT’s] into the metaverse. This integration allows metaverse to participants walk around utilizing their NFT’s as pseudonymous identities. To import an NFT into the metaverse, some platforms require that the API’s for a given collection offer an endpoint that serves the NFT image with the background removed or transparent. Now in theory, this would be as easy as asking Berk for the set of original background-less images that the GAN initially produced. The problem was that most of the bgans were trained with colored backgrounds, so the outputs already had colors merged with the figures, erasing the possibility of separating them easily! Only a set of ~4000 BGANS existed that had no background, but that set wasn't 100% included in the final published BGAN collection. The community considered manually removing the backgrounds, but at 11305 images, not counting each frame of the Hypes, it was a monumental proposal. There had to be a better way, if only a machine could somehow learn… how to remove a background. This is where Witrebel came in. He coded a machine-learning AI that when matched with a human participant could remove these backgrounds! In commemoration of his success and to reward participation we have a POAP!