World Congress 2022 Jun 15, 2022

DALL·E Flow: when neural search meets generative art

Han Xiao

Moving AI from experimental scripts to production-ready applications demands robust DevOps. Explore how DALL-E Flow leverages neural search and microservices to scale generative art seamlessly.

Pause
Mute Enter Fullscreen
#1 about 3 min

Exploring text prompts to generate artwork dynamically

Providing a text prompt to an AI program allows users to instantly generate entirely unique art assets.

#2 about 6 min

Building neural search applications across diverse data modalities

Implementing neural search capabilities enables fetching related content across fuzzy text, static e-commerce images, and 3D meshes.

#3 about 2 min

Utilizing deep learning for unstructured data retrieval

Neural search explores vector relationships between different unstructured data modalities to bring advanced retrieval systems into practical production environments.

#4 about 3 min

Identifying foundational machine learning technologies powering DALL-E

Understanding generative models requires tracking the architectural evolution of BERT, VQGAN, CLIP, and diffusion priors.

#5 about 3 min

Applying diffusion models for image upscaling and refinement

Diffusion architectures utilize Markov chains to systematically reconstruct high-quality visual details from added gaussian noise.

#6 about 2 min

Unifying neural search and generative model contexts

Both technologies operate under cross-modal boundaries by either matching against existing data sets or computing new contextual content.

#7 about 4 min

Structuring scalable cross-modal applications with Jina abstractions

Leveraging document, executor, and flow layers inside framework ecosystems simplifies building and orchestrating highly scalable machine learning microservices.

#8 about 3 min

Managing complex dependencies through cloud native orchestration

Containerizing deep learning logic removes local environment conflicts and establishes necessary observability pipelines for rapid production deployments.

#9 about 2 min

Orchestrating generative configurations using standardized YAML files

Defining logical executors through declarative YAML layouts quickly connects AI models into cohesive, docker-compatible inference runtimes.

#10 about 3 min

Iterating visual prototypes through a Google Colab pipeline

Generating text-to-image candidates and re-ranking them natively with CLIP guarantees higher accuracy before moving tasks to diffusion upscaling.

#11 about 3 min

Migrating from symbolic search layers to neural retrieval

Adopting neural frameworks unblocks complex cross-modal workflows that traditional term-frequency indexing engines fundamentally cannot support.

Matching moments

1:37 min

Exploring common use cases for modern generative AI

Sandra Ahlgrimm Sandra Ahlgrimm +1 · World Congress 2024

2:31 min

Integrating generative AI into cloud-native applications

Cedric Clyburn Cedric Clyburn · World Congress 2024

3:00 min

Introduction to generative AI and vector search

Mary Grygleski Mary Grygleski · LIVE

3:36 min

Overview of generative AI and the presentation agenda

juarezjunior juarezjunior · World Congress 2024

5:05 min

Exploring popular generative AI models and applications

Mary Grygleski Mary Grygleski · LIVE

3:47 min

Examples of generative AI applications in media and code

Cheuk Ho · World Congress 2023

Upcoming sessions on this topic

Open session

World Congress 2026 North America

September 23, 2026 · 10:00–17:00

Stage 11

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben
Open session

World Congress 2026 North America

September 25, 2026 · 09:00–09:30

Outdoor Stage

Where Judgment Went — and How to Put It Back

Shruti Tiwari

AI/ML product manager, Dell

Shruti Tiwari
Open session

World Congress 2026 North America

September 24, 2026 · 14:10–14:40

Stage 5

Edge AI: Running Agentic Intelligence Where Internet Can't Reach

Nitin Eusebius

AWS - Principal Solutions Architect

Nitin Eusebius
Open session

World Congress 2026 North America

September 24, 2026 · 11:00–11:30

Stage 3

Making Science Larger, not just Faster

Yuval Dvir

Commercial Executive, SandboxAQ

Yuval Dvir
Open session

World Congress 2026 North America

September 24, 2026 · 11:00–11:30

Stage 1

Application-Defined Compute: Rethinking Infrastructure for AI Applications

Anurag Goel

Founder & CEO of Render

Anurag Goel
Open session

World Congress 2026 North America

September 25, 2026 · 09:40–10:10

Stage 7

Loop Engineering

Li Yin

CEO

Li Yin