Categories: FAANG

DALL·E: Introducing Outpainting

Extend creativity and tell a bigger story with DALL-E images of any size

Original outpainting by Emma Catnip

Today we’re introducing Outpainting, a new feature which helps users extend their creativity by continuing an image beyond its original borders — adding visual elements in the same style, or taking a story in new directions — simply by using a natural language description.

if (value === 'end-result') { endResult.style.display = 'block'; timelapse.style.display = 'none'; timelapse.pause(); timelapse.currentTime = 0; } else if (value === 'timelapse') { endResult.style.display = 'none'; timelapse.style.display = 'block'; timelapse.play(); } }





Original: Girl with a Pearl Earring by Johannes Vermeer
Outpainting: August Kamp

DALL·E’s Edit feature already enables changes within a generated or uploaded image — a capability known as Inpainting. Now, with Outpainting, users can extend the original image, creating large-scale images in any aspect ratio. Outpainting takes into account the image’s existing visual elements — including shadows, reflections, and textures — to maintain the context of the original image.

More than one million people are using DALL·E, the AI system that generates original images and artwork from a natural language description, as a creative tool today. Artists have already created remarkable images with the new Outpainting feature, and helped us better understand its capabilities in the process.

Original outpainting by Tyna Eloundou
Original outpainting by OpenAI
Outpainting by David Schnurr
Original outpainting by Sonia Levesque
Original outpainting by Danielle Baskin
Original outpainting by Danielle Baskin
Original outpainting by Chad Nelson

Outpainting is now available to all DALL·E users on desktop. To discover new realms of creativity, visit labs.openai.com or join the waitlist.


Featured artists:

Emma Catnip


View Profile

August Kamp


View Profile

Sonia Levesque


View Profile

Danielle Baskin


View Profile

Chad Nelson


View Profile

class Painting { expanded = false;

constructor(el) { this.el = el; this.image = el.querySelector('img');

this.el.addEventListener('click', () => { this.toggle(); }); }

toggle(value) { if (!isMobile) { return; }

if (value === undefined) { value = !this.expanded; }

if (value) { this.expand(); } else { this.collapse(); }

this.expanded = value; }

expand() { this.el.classList.add('expanded-painting'); this.el.scrollLeft = (0.5 * this.image.offsetWidth) - (0.5 * window.innerWidth); }

collapse() { this.el.classList.remove('expanded-painting'); } }

document.addEventListener('DOMContentLoaded', function() { isMobile = window.innerWidth < 720; const paintings = Array.from(document.querySelectorAll('.js-painting')).map(el => new Painting(el));

window.addEventListener('resize', () => { const newIsMobile = window.innerWidth < 720; // Make sure all paintings are collapsed again, // we're entering larger viewports if (newIsMobile !== isMobile && !newIsMobile) { paintings.forEach((painting) => { painting.collapse(); }); }

isMobile = newIsMobile; });

if (!el) return; var flickity = new Flickity(el, { cellSelector: '.js-flickity-cell', wrapAround: false, autoPlay: false, draggable: true, adaptiveHeight: true, arrowShape: 'M 64.5,0 L 71.72,7.17 L 29.22,50 L 71.72,92.89 L 64.5,100 L 15,50 L 64.5,0 Z', imagesLoaded: true, }); });

AI Generated Robotic Content

Recent Posts

[Sad] Zelda & Link don’t want to be toys anymore / MiniMax H3 Video

I know people aren't posting their videos made with MiniMax H3 anymore... Which is really…

13 hours ago

Building a Custom LLM Evaluation Harness in Python from Scratch

In this article, you will learn how to build a custom LLM evaluation harness in…

13 hours ago

The Design Space of Tri-Modal Masked Diffusion Models

Discrete diffusion models have emerged as strong alternatives to autoregressive language models, with recent work…

13 hours ago

Integrating Netflix’s Foundation Model into Personalization applications

Authors: Divya Gadde, Ko-Jen Hsiao, Dhaval Patel and Moumita BhattacharyaThe motivation for building the Netflix…

13 hours ago

Build self-improving document processing using Amazon Bedrock AgentCore

IDC research shows that document-related challenges cost organizations $19,732 for each information worker annually and…

13 hours ago

Predictable AI spend in BigQuery: Introducing cost management for generative AI functions

The generative AI functions in BigQuery (AI.GENERATE, AI.IF, AI.CLASSIFY, AI.SCORE, and more) bring large language…

13 hours ago