At the Augmented World Expo, Snap showcased a real-time, on-device image diffusion model for generating vivid AR experiences. Snap’s co-founder and CTO, Bobby Murphy, revealed that the model can run on smartphones and re-render frames in real time based on text prompts. The company also introduced generative AI tools for AR creators to enhance their work.
Murphy emphasized the need for faster generative AI models to make a significant impact on augmented reality. Snapchat users can expect to see Lenses with this new model in the coming months, with plans to make it available to creators by the end of the year. The new technology is expected to revolutionize AR experiences and accelerate the creation process for developers.
Lens Studio 5.0 was also announced, offering developers access to new generative AI tools to create AR effects more efficiently. These tools allow creators to generate realistic ML face effects, custom stylization effects, 3D assets, and characters like aliens or wizards using Face Mesh technology. The AI assistant in Lens Studio can provide answers to questions that AR creators may have, making the creation process more streamlined and efficient. Overall, these advancements in AR technology are set to transform the way AR experiences are rendered and created.
Source link
Source link: https://techcrunch.com/2024/06/18/snap-previews-its-real-time-image-model-that-can-generate-ar-experiences/