advertisement
advertisement

This AI designs Balenciaga better than Balenciaga

It’s really into asymmetry and color-blocking.

This AI designs Balenciaga better than Balenciaga
[Image: Robbie Barat]

Right now, designer fashion houses are gearing up for New York Fashion Week in September. But on Twitter, fashion week came early, courtesy of a clever neural network.

advertisement
advertisement

The AI, created by artist Robbie Barrat, has created an entire collection based on Balenciaga’s previous styles. There’s a fabulous pink and red gradient jumpsuit that wraps all the way around the model’s feet–like a onesie for fashionistas–paired with a dark slouchy coat. There’s a textural color-blocked dress, paired with aqua-green tights. And for menswear, there’s a multi-colored, shimmery button-up with skinny jeans and mismatched shoes. None of these looks would be out of place on the runway.

To create the styles, Barrat collected images of Balenciaga’s designs via the designer’s lookbooks, ad campaigns, runway shows, and online catalog over the last two months, and then used them to train the pix2pix neural net. While some of the images closely resemble humans wearing fashionable clothes, many others are a bit off–some models are missing distinct limbs, and don’t get me started on how creepy their faces are. Even if the outfits aren’t quite ready to be fabricated, Barrat thinks that designers could potentially use a tool like this to find inspiration. Because it’s not constrained by human taste, style, and history, the AI comes up with designs that may never occur to a person. “I love how the network doesn’t really understand or care about symmetry,” Barrat writes on Twitter.

One image shows a woman in a two-tone dress carrying what appears to be a tassel that matches part of her outfit, rather than a purse. “Sure you can just pass it off as some blunder by the network, but stuff like just carrying a matching tassel/piece of cloth around is so utterly detached from everyday human life,” Barrat writes. “I don’t know how anything *except* a neural network could come up with something like this.”

You can check out the full collection on his Twitter here.

advertisement
advertisement

About the author

Katharine Schwab is an associate editor based in New York who covers technology, design, and culture. Email her at kschwab@fastcompany.com and sign up for her newsletter here: https://tinyletter.com/schwabability

More