Presti Bring AI-Generated Lifestyle Photos for E-commerce

Have you ever considered the backgrounds in furniture product photos when shopping for sofas online? Furniture companies typically invest significant resources in photo shoots when launching new collections. This process is often costly and challenging due to the difficulties in moving large furniture items.

Recognizing this issue, a French startup named Presti, established in November 2022, has developed a solution using generative AI. Their technology can transform a single product image into a lifelike lifestyle photograph. The company has recently secured $3.5 million in seed funding, with global tech investment firm Partech leading the round and various business angels contributing.

“Very quickly, we picked up the phone and talked with 50 potential users,” Presti co-founder and CEO Nabil Toumi said, “And everyone was saying the same thing. Creating product visuals was a process that took a very long time, cost a lot of money and they didn’t have a simple solution for creating these photos. At the same time, it was really the most important asset for brands so that they can create a unique identity and sell online.”

Presti turns this image:-

Into this:-

Initially, Presti’s target market was not specifically focused on furniture companies. However, the startup soon identified that businesses in the furniture industry were grappling with some uniquely challenging issues.

“For a photoshoot, they needed to rent a nice house, they needed to transport products — so they had high logistics costs associated with that. And those photo shoots were planned months in advance and ended up costing them hundreds of thousands, even millions of euros a year,” Toumi said.

Presti’s core technology is built on Stable Diffusion XL as its base model. The company has refined and retrained this model to specifically cater to product imagery needs in the furniture sector.

Initially, the team experimented with an unmodified version of Stable Diffusion XL. However, they soon encountered challenges. As Toumi explained, “You’re going to have legs added to your sofa, and the backrest will be distorted.” Additionally, achieving accurate perspective proved difficult. For example, ensuring that the wall behind a sofa appears parallel to the furniture piece was problematic.

“At the same time, something that is really important is the dataset on which we’ve trained our model. We currently have over 75,000 images of ultra-high quality photos of furniture in our industry, which we can use to train our model to reinforce the learning process for a specific use case, for this type of photo,” said Toumi.

Presti’s capabilities extend beyond background generation. Users can incorporate accessories into their images, such as cushions for a sofa. These added elements create realistic shadows, avoiding the artificial appearance often associated with Photoshop additions.

The company is also developing features to address the common practice of furniture brands offering multiple variations of a single model with different textures and colors. Although still in development, Presti aims to allow customers to easily swap materials using their tool, potentially streamlining the process of releasing new products.

However, this technology may have negative implications for freelance photographers. Additionally, it remains to be seen whether the creativity and uniqueness brought by skilled professionals like location stylists in physical photo shoots can be fully replicated by machine-generated backgrounds without resulting in homogeneous artificial lifestyle images.

While Presti primarily serves mid-sized furniture companies, it has also established a strategic partnership with Maisons du Monde, a major furniture retailer in France. In addition to Partech’s investment, the startup has attracted funding from individual investors including Maxime Brousse, Thibaud Elzière, Julien Hirth, Abou Laraki, and Rémi Lemonnier.