DALL·E Flow: when neural search meets generative art

Google Munich Office - Erika-Mann-Straße 33 Munich, 80636 - View Map Technical University of Munich
Wed, Jun 1, 2022, 5:45 PM (CEST)

About this event

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 networks becomes extremely straightforward. DALL·E, a powerful image-to-text generator released by OpenAI in 2021 further boosts the popularity of multimodal applications. We now see thousands of astonishing artwork made by DALL·E every day. How all these new technologies will change the way of comprehending multi-/cross modal data?

This event is bi-partite.

  • In part 1, Dr. Han Xiao will break down 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. He will use it to demonstrate how Jina unlocks multi-modal/cross-modal capability in your solution & applications.
  • In part 2, we will run a 45-min competition (Please bring your laptop!): participants will use DALL·E Flow on Google Colab to create their artworks with the chance to win amazing Jina AI swags! This is a great chance to get hands dirty with Jina and DocArray's Pythonic API and to embrace the charm of generative arts. All artworks will be collected and voted at the end. 

Note: There is no prior knowledge for attending this event. Basic Python skills should be enough to participate in part 2 hands-on session.

We are excited to host a hybrid event this time again and there are two types of tickets: on-site and virtual:

  • If you apply for the on-site ticket, please also confirm that you will come to the on-site event reliably via the application form. In case you cannot make it to the event in person due to an unforeseen reason, please un-RSVP on our website (or reach out to dsc.munich@gmail.com) in time so they can free up the space for someone else. You will get a reminder email 1-2 days before the event on how to arrive at the Google office.
  • If there are no tickets left for the on-site event, you can join the waiting list. If a ticket gets free we will notify you and you can RSVP.
  • If you decide to apply for the virtual ticket, you will see the link for the Google Meet live stream on the event website 15 min before the event starts!

If you wish to stay up to date with events, become part of our GDSC community (900+ members) by clicking the 'Join us' button at https://gdsc.community.dev/technical-university-of-munich/ 



Wednesday, Jun 1
5:45 PM - 9:30 PM (CEST)


Google Munich Office
Erika-Mann-Straße 33 Munich80636