Landing AI Launches the World’s First Commercial Visual Prompting Capability in LandingLens

The ChatGPT of computer vision learns in seconds, deploys in minutes: re-trained transformer model enables visual conversations leading to AI-generated results

Palo Alto, CA — April 25, 2023 — Landing AI, the Computer Vision Cloud company, announced today the launch of its revolutionary Visual Prompting capability. This technology takes the framework of text prompting found in technologies such as ChatGPT and brings it to computer vision. This technology shift enables users to have visual conversations via Visual Prompting to build computer vision systems.

The traditional AI workflow requires multiple steps: finding and labeling data, training a model, and then making predictions. This is typically a very long and multi-step process in which feedback is often given very late in the cycle. In contrast, text interfaces like ChatGPT have a dramatically simpler process in which users give text prompts saying what they want, and get answers quickly. Then users can rapidly iterate with ChatGPT to get more insights or clarity. In a similar vein, Visual Prompting significantly reduces the time to get a computer vision result from days or months to minutes or even seconds.

With Visual Prompting, going from specifying the prompt (labeling a few pixels of one or more images) to getting predictions happens almost instantaneously. Instead of taking hours to label, train and make predictions, the user can start getting predictions in seconds. If the initial results are not satisfactory, the user can immediately label a few more small areas that they want the AI system to better recognize to quickly improve the results.

Hummingbird Detection App created by Visual Prompting

“Prompting started with text and gave users a very different way to interact with AI systems. Visual Prompting takes this technology transformation from text to images.” said Andrew Ng, Founder and CEO of Landing AI. 

Landing AI’s Visual Prompting is available as a public beta now, and expects to quickly improve based on user and customer feedback and interactions. The company has partnered with users in multiple industries, including manufacturing, life sciences, satellite imagery, and retail to apply this technology. This is another step in Landing AI’s mission to democratize the creation of AI and make it easier for everyone to use custom AI systems tuned to their own data and applications. 

“We are grateful for the continued dedication of the Landing AI team in their pursuit of streamlining AI workflows,” says Bob Chen, Sr Director at OmniAb. “With Visual Prompting, our team is able to build new models with greater ease, which allows us to build tailored models for new applications of our technology. The greatest impact of Visual Prompting has been in use cases where it would be laborious to exhaustively label all features, such as cells in our high throughput screening platform. Thanks to Visual Prompting’s intuitive prompt interface, we can achieve high-quality results in a fraction of the time and with significantly reduced effort.”

This breakthrough technology was developed by Landing AI’s team of experts in computer vision and natural language processing (NLP). The key to this technology is a large pre-trained vision transformer model, which enables the AI to make inferences from just a simple Visual Prompt input. By blending the best of foundation models like Meta’s SAM with Landing AI’s deep tech – the first enterprise-grade Visual Prompting is available at www.landing.ai for everyone worldwide.

Additional Visual Prompting Resources

• Join our livestream today at 10 am PT where Andrew Ng discusses Visual Prompting
• Start Free Trial
• Join the conversation in the Landing AI community

About Landing AI

Landing AI™ is democratizing the creation of AI in computer vision projects. Even with limited data sets, companies realize the value of AI and move AI projects from proof-of-concept to production. Guided by a data-centric AI approach, Landing AI’s flagship product is LandingLens™, a computer vision cloud platform that enables users to build, iterate and deploy computer vision solutions quickly and easily. With data quality being key to the success of production AI systems, LandingLens™ enables users to achieve optimal data accuracy and consistency. Founded by Andrew Ng, co-founder of Coursera, founding lead of Google Brain, and former chief scientist of Baidu, Landing AI is uniquely positioned to lead the development of AI from a technology that benefits a few to a technology that benefits all. Get started for free: www.landing.ai.