{"id":2892,"date":"2022-12-15T07:50:49","date_gmt":"2022-12-15T07:50:49","guid":{"rendered":"https:\/\/toshareproject.it\/artmakerblog\/?p=2892"},"modified":"2022-12-15T07:50:49","modified_gmt":"2022-12-15T07:50:49","slug":"jon-evans-explaining-how-text-to-image-generators-work","status":"publish","type":"post","link":"https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/","title":{"rendered":"Jon Evans explaining how text-to-image generators work"},"content":{"rendered":"<p>*That&#8217;s a noble effort at explication there, and well worth a read.<\/p>\n<p><a href=\"https:\/\/aiascendant.substack.com\/p\/how-dall-e-works-part-2\">https:\/\/aiascendant.substack.com\/p\/how-dall-e-works-part-2<\/a><\/p>\n<p>(&#8230;)<\/p>\n<p>This is where the magic happens. Suppose the diffusion process with which you trained your model had 1,000 steps, invariably ending after the thousandth in pure Gaussian noise, seemingly incomprehensible random chaos. Well, if you show your trained model some of that pure noise \u2026 it has learned how to estimate the change since the step just before random chaos. You can then remove that estimated noise from the pure randomness, resulting in, in effect, the model\u2019s estimate of a 999th step, a point at which where there is the tiniest hint of structure, the merest suggestion of some kind of order. <\/p>\n<p>So far, so little. To the human eye, that estimated 999th step will still be indistinguishable from chaos. But\u2026<\/p>\n<p>\u2026then you run that estimated 999th step through the network again, to generate an estimated 998th step \u2026 and then a 997th \u2026 and very slowly, step by step, patterns begin to appear which seem non-random, and then, ultimately, recognizable to the human eye \u2026 forms, then shapes, then images, even faces \u2026 and eventually, after a thousand backwards steps, you wind up with a glorious, brand-new image, generated on the spot. Brand-new because, remember, the neural network estimates the added noise, rather than making precise calculations, so every input will lead to new estimation fuzziness at each step, and ultimately a different result.<\/p>\n<p>In the end, as you\u2019ve no doubt witnessed, the generated DALL-E image can be as photorealistic, as apparently seamless, as any of the original set of high-quality, human-generated images on which the diffusion model was initially trained. It feels like sorcery! But it\u2019s really just a huge number of very repetitive, quite simple mathematical calculations \u2026 which accumulate into enormous power and subtlety&#8230;.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>*That&#8217;s a noble effort at explication there, and well worth a read. https:\/\/aiascendant.substack.com\/p\/how-dall-e-works-part-2 (&#8230;) This is where the magic happens. Suppose the diffusion process with which you trained your model had 1,000 steps, invariably ending after the thousandth in pure Gaussian noise, seemingly incomprehensible random chaos. Well, if you show your trained model some of [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-2892","post","type-post","status-publish","format-standard","hentry","category-uncategorised"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v17.0 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Jon Evans explaining how text-to-image generators work | Artmaker Blog<\/title>\n<meta name=\"description\" content=\"Jon Evans explaining how text-to-image generators work | Artmaker Blog\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Jon Evans explaining how text-to-image generators work | Artmaker Blog\" \/>\n<meta property=\"og:description\" content=\"Jon Evans explaining how text-to-image generators work | Artmaker Blog\" \/>\n<meta property=\"og:url\" content=\"https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/\" \/>\n<meta property=\"og:site_name\" content=\"Artmaker Blog\" \/>\n<meta property=\"article:published_time\" content=\"2022-12-15T07:50:49+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Bruce Sterling\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebSite\",\"@id\":\"https:\/\/toshareproject.it\/artmakerblog\/#website\",\"url\":\"https:\/\/toshareproject.it\/artmakerblog\/\",\"name\":\"Artmaker Blog\",\"description\":\"on Toshareproject.it - curated by Bruce Sterling\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/toshareproject.it\/artmakerblog\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-GB\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/#webpage\",\"url\":\"https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/\",\"name\":\"Jon Evans explaining how text-to-image generators work | Artmaker Blog\",\"isPartOf\":{\"@id\":\"https:\/\/toshareproject.it\/artmakerblog\/#website\"},\"datePublished\":\"2022-12-15T07:50:49+00:00\",\"dateModified\":\"2022-12-15T07:50:49+00:00\",\"author\":{\"@id\":\"https:\/\/toshareproject.it\/artmakerblog\/#\/schema\/person\/6f20726ed2761431f3e0ff4e096c3085\"},\"description\":\"Jon Evans explaining how text-to-image generators work | Artmaker Blog\",\"breadcrumb\":{\"@id\":\"https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/toshareproject.it\/artmakerblog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Jon Evans explaining how text-to-image generators work\"}]},{\"@type\":\"Person\",\"@id\":\"https:\/\/toshareproject.it\/artmakerblog\/#\/schema\/person\/6f20726ed2761431f3e0ff4e096c3085\",\"name\":\"Bruce Sterling\",\"image\":{\"@type\":\"ImageObject\",\"@id\":\"https:\/\/toshareproject.it\/artmakerblog\/#personlogo\",\"inLanguage\":\"en-GB\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/c390e8ed4db57a34278dcf667f928a643cf769a865c8a8632dcd310412bb9a99?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/c390e8ed4db57a34278dcf667f928a643cf769a865c8a8632dcd310412bb9a99?s=96&d=mm&r=g\",\"caption\":\"Bruce Sterling\"},\"description\":\"Art director at Share Festival, author and journalist\",\"sameAs\":[\"http:\/\/toshareproject.it\/tomorrowart\"],\"url\":\"https:\/\/toshareproject.it\/artmakerblog\/author\/brucesterling\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Jon Evans explaining how text-to-image generators work | Artmaker Blog","description":"Jon Evans explaining how text-to-image generators work | Artmaker Blog","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/","og_locale":"en_GB","og_type":"article","og_title":"Jon Evans explaining how text-to-image generators work | Artmaker Blog","og_description":"Jon Evans explaining how text-to-image generators work | Artmaker Blog","og_url":"https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/","og_site_name":"Artmaker Blog","article_published_time":"2022-12-15T07:50:49+00:00","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Bruce Sterling","Estimated reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebSite","@id":"https:\/\/toshareproject.it\/artmakerblog\/#website","url":"https:\/\/toshareproject.it\/artmakerblog\/","name":"Artmaker Blog","description":"on Toshareproject.it - curated by Bruce Sterling","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/toshareproject.it\/artmakerblog\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-GB"},{"@type":"WebPage","@id":"https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/#webpage","url":"https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/","name":"Jon Evans explaining how text-to-image generators work | Artmaker Blog","isPartOf":{"@id":"https:\/\/toshareproject.it\/artmakerblog\/#website"},"datePublished":"2022-12-15T07:50:49+00:00","dateModified":"2022-12-15T07:50:49+00:00","author":{"@id":"https:\/\/toshareproject.it\/artmakerblog\/#\/schema\/person\/6f20726ed2761431f3e0ff4e096c3085"},"description":"Jon Evans explaining how text-to-image generators work | Artmaker Blog","breadcrumb":{"@id":"https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/toshareproject.it\/artmakerblog\/jon-evans-explaining-how-text-to-image-generators-work\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/toshareproject.it\/artmakerblog\/"},{"@type":"ListItem","position":2,"name":"Jon Evans explaining how text-to-image generators work"}]},{"@type":"Person","@id":"https:\/\/toshareproject.it\/artmakerblog\/#\/schema\/person\/6f20726ed2761431f3e0ff4e096c3085","name":"Bruce Sterling","image":{"@type":"ImageObject","@id":"https:\/\/toshareproject.it\/artmakerblog\/#personlogo","inLanguage":"en-GB","url":"https:\/\/secure.gravatar.com\/avatar\/c390e8ed4db57a34278dcf667f928a643cf769a865c8a8632dcd310412bb9a99?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/c390e8ed4db57a34278dcf667f928a643cf769a865c8a8632dcd310412bb9a99?s=96&d=mm&r=g","caption":"Bruce Sterling"},"description":"Art director at Share Festival, author and journalist","sameAs":["http:\/\/toshareproject.it\/tomorrowart"],"url":"https:\/\/toshareproject.it\/artmakerblog\/author\/brucesterling\/"}]}},"_links":{"self":[{"href":"https:\/\/toshareproject.it\/artmakerblog\/wp-json\/wp\/v2\/posts\/2892","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/toshareproject.it\/artmakerblog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/toshareproject.it\/artmakerblog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/toshareproject.it\/artmakerblog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/toshareproject.it\/artmakerblog\/wp-json\/wp\/v2\/comments?post=2892"}],"version-history":[{"count":1,"href":"https:\/\/toshareproject.it\/artmakerblog\/wp-json\/wp\/v2\/posts\/2892\/revisions"}],"predecessor-version":[{"id":2893,"href":"https:\/\/toshareproject.it\/artmakerblog\/wp-json\/wp\/v2\/posts\/2892\/revisions\/2893"}],"wp:attachment":[{"href":"https:\/\/toshareproject.it\/artmakerblog\/wp-json\/wp\/v2\/media?parent=2892"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/toshareproject.it\/artmakerblog\/wp-json\/wp\/v2\/categories?post=2892"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/toshareproject.it\/artmakerblog\/wp-json\/wp\/v2\/tags?post=2892"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}