Abstract

Neural search - the technology of using deep learning to search unstructured data, has developed rapidly in the last two years. With a framework like Jina (https://github.com/jina-ai/jina), searching cross-modal/multi-modal data via deep neural network becomes extremely straightforward. DALL·E, a powerful image-to-text generator released by OpenAI in 2021 further boosts the popularity of multimodal application.

We now see thousands of astonishing artwork made by DALL·E every day. In this talk, I will breakdown the design and implementation of DALL·E Flow (https://github.com/jina-ai/dalle-flow): a Human-in-the-Loop workflow for creating HD images from text. I will use it as an example to demonstrate how Jina unlocks multi-modal/cross-modal capability in your business and solution.