If you happen to’ve ever purchased a settee on-line, have you considered the properties you may see within the background of the product photographs? When it’s time to launch a brand new assortment, furnishings manufacturers normally spend a small fortune on photograph shoots. It’s a cumbersome and costly course of because it’s not simple to maneuver furnishings round.
That’s why a French startup known as Presti, based in November 2022, is utilizing generative AI to show a single product picture into a practical life-style photograph. The corporate has simply raised a $3.5 million seed spherical led by the worldwide tech funding agency Partech, with a number of enterprise angels additionally taking part.
“In a short time, we picked up the telephone and talked with 50 potential customers,” Presti co-founder and CEO Nabil Toumi informed TechCrunch. “And everybody was saying the identical factor. Creating product visuals was a course of that took a really very long time, price some huge cash and so they didn’t have a easy resolution for creating these photographs. On the similar time, it was actually a very powerful asset for manufacturers in order that they will create a singular identification and promote on-line.”
Presti turns this:
Into this:
At first, Presti didn’t slender down its focus to furnishings firms. However the startup shortly realized that furnishings firms confronted some notably troublesome ache factors.
“For a photoshoot, they wanted to hire a pleasant home, they wanted to move merchandise — so that they had excessive logistics prices related to that. And people photograph shoots had been deliberate months upfront and ended up costing them a whole bunch of hundreds, even hundreds of thousands of euros a 12 months,” Toumi stated.
At its core, Presti makes use of Secure Diffusion XL as its basis mannequin. It has been retrained and tweaked in order that it really works notably nicely for product imagery within the furnishings business.
At first, the workforce tried to make use of a vanilla model of Secure Diffusion XL. However they shortly realized that there have been points. “You’re going to have legs added to your couch, and the backrest will likely be distorted,” Toumi stated. Equally, it was onerous to get the attitude proper. For example, the wall behind the couch must be parallel to the couch.
“On the similar time, one thing that’s actually essential is the dataset on which we’ve educated our mannequin. We at the moment have over 75,000 pictures of ultra-high high quality photographs of furnishings in our business, which we are able to use to coach our mannequin to strengthen the educational course of for a particular use case, for any such photograph,” Toumi stated.
Presti didn’t need to cease at background technology. Prospects may add equipment. For example, should you’re producing product photographs for a brand new couch, you may add cushions. These cushions will mission a practical shadow on the couch so that they don’t appear like one thing that was added in Photoshop.
Equally, furnishings manufacturers normally have a number of variations of the identical mannequin with totally different textures and colours. Whereas that is nonetheless a piece in progress, Presti hopes its clients will be capable to swap the fabric utilizing its device. In consequence, it’s going to be a lot simpler for firms utilizing Presti to launch new merchandise.
On the flip aspect, freelance photographers aren’t going to love this new product, although. And whether or not the creativity and originality that different expert people who may match on a bodily photograph shoot, reminiscent of location stylists, could be fully changed by way of machine-generated backgrounds — with out the ensuing synthetic life-style pictures trying a bit same-y — is one open query.
Whereas Presti largely works with mid-sized furnishings firms, it additionally has a strategic partnership with Maisons du Monde, one of many largest furnishings retailers in France. Along with Partech, different buyers within the startup embrace Maxime Brousse, Thibaud Elzière, Julien Hirth, Abou Laraki and Rémi Lemonnier.
