From toy to tool: DALL-E 3 is a wake-up call for visual artists—and the rest of us

D October i OpenAI I model that uses a t AI hnique called latent dif 3 usion to pull images it "recognizes" out of noise.

You tell ChatGPT what you'd like it to generate, and it writes ideal two years ago ou and submits them to the backend.

You can also change the aspect ratio of the generated image from the square default to "wide" (16:9) or "tall" (9 this long ago lass="summaryFeed_highLightText__NxlGi">GPT-4V GPT-4 AI xt__NxlGi">GPT-4V Aurich Lawson LightT Technica Gi">OpenAI 3 AI OpenAI AI pan class="summaryFeed_highLightText__NxlGi">AI metadata AI Shutterstock AI aryFeed_highLightText__NxlGi">hundreds of millions AI lGi">OpenAI first lass="summaryFee 3 _highLightText__NxlGi">3OpenAI span late September yFeed_highLightText__NxlGi">OpenAI 3 xt__Nxl AI ">9:16 16:9 two GPT-4 AI Stable Diffusion an cl Midjourney ryFeed_highLightText__NxlGi">3