Categories: News

Snapchat’s Latest AI Innovation Lets you Design Lenses with Description

Snap, Snapchat’s parent company, is expanding its suite of AI tools for creators.

At this year’s Snap Partner Summit in Santa Monica, California, Snap announced a new feature, Easy Lens, that translates plain-English descriptions into Lenses, Snap’s brand of augmented reality (AR) objects, 3D effects, characters, and transformations for photos and videos. Available in Snap’s developer platform, Lens Studio, Easy Lens taps generative AI models to parse what you write and automatically build a Lens using Lens Studio components.

Elsewhere in Lens Studio, Snap is rolling out Body Morph, a generative tool for creating 3D characters, costumes, and outfits from a text caption or reference image. An image generator specifically to create icons for Lenses is also coming to Lens Studio, as well as hundreds of animations for Bitmoji — the personalized emoji on Snapchat — that can be stitched together using a new blending feature.

Image Credits:Snap

In the future, Snap says, it’ll add even more generative capabilities to Lens Studio, including a custom animation generator and a tool that’ll let creators upload a video of an object to Lens Studio to have the software reconstruct that object as a 3D asset.

In a recent memo, Snap CEO Evan Spiegel emphasized that the company, which has invested heavily in generative AI, continues to see the technology as “transformative” to Snap’s various properties. In fact, Spiegel contended that generative AI is responsible in large part for driving Snap’s creator growth.

Image Credits:Snap

“Our AI Lenses are already some of the most used Lenses on Snapchat, and our on-devices model will allow us to further scale these experiences with faster generation and lower cost,” Spiegel wrote. “This year brings many more opportunities to further improve identity preservation in generative Snaps, enable generative video experiences and help people reinterpret and reimagine their [Snapchat] Memories in new ways.”

The number of creators publishing Lenses grew to 375,000 as of this month, Snap says, up from 330,000 last November. Meanwhile, the number of Lenses across Snapchat, websites, mobile apps, and Snap’s AR glasses, Spectacles, climbed from 3.5 million to 4 million over the same period.

Image Credits:Snap

Snap’s under pressure to perform. The company’s Q3 earnings came in below market estimates, in large part due to a flagging ad market. (Snap gets nearly all of its revenue from advertising.) In a single day in August, the company lost more than $4.6 billion in market value as its shares plummeted.

In the memo, Spiegel said that, in addition to exploring new avenues for generative AI across its products, Snap plans to test several new ad formats to boost advertiser interest and a “simplified” version of the Snapchat app.

admage

Share
Published by
admage

Recent Posts

InstantIR: Restore Your Images

Figuring out the model that can fix your low quality pictures? Now, restoring your low…

4 days ago

Omnigen: Next-Gen Image Generation & Editing Tool

Traditional diffusion models uses various mechanisms for image modification like ControlNet, IP-Adapter, Inpainting, Face detection,…

1 week ago

Create Engaging Videos with Mochi1

Mochi 1, an open-source text-to-video diffusion model has been released by Genmo.  Trained with 10…

3 weeks ago

Local Installation of Stable Diffusion 3.5

So, it's finally here. Stable Diffusion 3.5 has been released by StabilityAI on October 22nd,…

4 weeks ago

Video Depth Mapper: Efficient 3D Depth Mapping Solution

Due to the extreme diversity of video content like motion, camera panning, and length, the…

1 month ago

Top 30 Negative Prompts for Reliable Diffusion Models

 You can use these negative prompts while generating images using Stable Diffusion models.1. Clear BrandingPrompt:text,…

1 month ago