{"id":377,"date":"2023-07-07T10:00:00","date_gmt":"2023-07-07T10:00:00","guid":{"rendered":"https:\/\/jacar.es\/?p=377"},"modified":"2026-04-19T20:32:28","modified_gmt":"2026-04-19T18:32:28","slug":"stable-diffusion-xl","status":"publish","type":"post","link":"https:\/\/jacar.es\/en\/stable-diffusion-xl\/","title":{"rendered":"Stable Diffusion XL: Powerful Open Image Generation"},"content":{"rendered":"<p><a href=\"https:\/\/stability.ai\/\">Stability AI<\/a> released <strong>Stable Diffusion XL<\/strong> (SDXL) in July 2023, marking a significant leap in image-generation quality within the open-source family. Unlike Midjourney or DALL-E, SDXL ships with downloadable weights under a permissive license, making it attractive for teams that need control over where and how inference runs.<\/p>\n<h2 id=\"what-changes-vs-sd-1.52.1\">What Changes vs SD 1.5\/2.1<\/h2>\n<p>SDXL is a redesigned architecture. Three key differences from earlier models:<\/p>\n<ul>\n<li><strong>Size<\/strong>: 3.5 billion parameters in U-Net (base) + 6.6 billion in refiner, vs ~900M in SD 1.5. This explains both the quality jump and the increased hardware requirements.<\/li>\n<li><strong>Native resolution<\/strong>: trained at 1024\u00d71024, vs 512\u00d7512 for SD 1.5. Images have better composition and fewer upscaling artefacts.<\/li>\n<li><strong>Additional conditioning<\/strong>: SDXL takes as input not just the prompt but also the original crop size during training, reducing artefacts like duplicated limbs or illegible text.<\/li>\n<\/ul>\n<p>A less-obvious practical change: SDXL handles long prompts and specific details better. SD 1.5 saturated quickly with prompts over 30-40 tokens; SDXL flows with 75+ token prompts.<\/p>\n<h2 id=\"hardware-requirements\">Hardware Requirements<\/h2>\n<p>The open-source promise comes with hardware cost. SDXL runs realistically on:<\/p>\n<ul>\n<li><strong>NVIDIA GPU with 12+ GB VRAM<\/strong> (RTX 3060 12GB minimum; ideal RTX 4090).<\/li>\n<li><strong>Optional refiner<\/strong>: adds quality but doubles memory usage. Many workflows skip it after confirming base-model output is sufficient.<\/li>\n<li><strong>CPU alternatives<\/strong>: theoretically possible but take minutes per image instead of seconds.<\/li>\n<\/ul>\n<p>For those not wanting to manage GPUs, managed APIs \u2014 <a href=\"https:\/\/replicate.com\/\">Replicate<\/a>, <a href=\"https:\/\/www.together.ai\/\">Together AI<\/a>, <a href=\"https:\/\/platform.stability.ai\/\">Stability Cloud<\/a> \u2014 expose SDXL at ~0.01-0.05 USD per image depending on resolution.<\/p>\n<h2 id=\"practical-comparison-sdxl-vs-midjourney-vs-dall-e-3\">Practical Comparison: SDXL vs Midjourney vs DALL-E 3<\/h2>\n<p>Each generator has its profile:<\/p>\n<ul>\n<li><strong>SDXL<\/strong>: maximum technical control. Sampler, CFG scale, seed, ControlNet, custom LoRA adjustments. Ideal when you need reproducibility, style consistency across images, or integration into your own pipeline.<\/li>\n<li><strong><a href=\"https:\/\/www.midjourney.com\/\">Midjourney<\/a><\/strong>: best average aesthetic with no configuration. If you want \u201cthe pretty image by default\u201d, Midjourney wins. Less controllable, closed, via Discord.<\/li>\n<li><strong><a href=\"https:\/\/openai.com\/dall-e-3\">DALL-E 3<\/a><\/strong>: best natural-language prompt adherence. If you want \u201can orange cat with sunglasses sitting on a red leather sofa\u201d, DALL-E 3 interprets spatial relationships better than the other two.<\/li>\n<\/ul>\n<p>No absolute winner. Product teams often test all three in parallel with the same prompts before deciding which fits their use.<\/p>\n<h2 id=\"recommended-workflow\">Recommended Workflow<\/h2>\n<p>For serious SDXL use, a workflow that scales well:<\/p>\n<ol type=\"1\">\n<li><strong>Base prompt + style as LoRA<\/strong>. Train a LoRA (small fine-tune, ~50-200 images) with your brand\u2019s visual style. Then generate with base prompt + LoRA, ensuring visual consistency.<\/li>\n<li><strong>ControlNet for composition<\/strong>. When you need specific layout (say, product in foreground with blurred background), <a href=\"https:\/\/github.com\/lllyasviel\/ControlNet\">ControlNet<\/a> lets you condition generation with a sketch, pose skeleton, or depth map.<\/li>\n<li><strong>Refiner for the final pass<\/strong>. Two phases: generate with base model (faster), then pass the best candidates through refiner (slower but better detail on faces and textures).<\/li>\n<li><strong>Inpainting for targeted corrections<\/strong>. Instead of regenerating the whole image, replace only the problematic region (hands, text, specific objects).<\/li>\n<\/ol>\n<p>Tools like <a href=\"https:\/\/github.com\/AUTOMATIC1111\/stable-diffusion-webui\">Automatic1111 WebUI<\/a>, <a href=\"https:\/\/github.com\/comfyanonymous\/ComfyUI\">ComfyUI<\/a>, or <a href=\"https:\/\/github.com\/invoke-ai\/InvokeAI\">InvokeAI<\/a> wrap this flow with a UI; for production integrations, <a href=\"https:\/\/github.com\/huggingface\/diffusers\">diffusers<\/a> from Hugging Face gives programmatic control.<\/p>\n<h2 id=\"license-considerations\">License Considerations<\/h2>\n<p>SDXL is published under the <a href=\"https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md\">OpenRAIL++-M License<\/a> \u2014 allows commercial use but with restrictions on generating illegal, deceptive, or harmful content. For product use, review the clauses: they limit specific cases (non-consensual sexual content, deliberate disinformation), not general use.<\/p>\n<p>On the training of these models, the legal situation is active. Several <a href=\"https:\/\/www.theverge.com\/2023\/1\/16\/23557098\/generative-ai-art-copyright-legal-lawsuit-stable-diffusion-midjourney-deviantart\">lawsuits<\/a> question whether training on copyrighted images without licence complies with copyright law. Outcomes will likely affect the whole ecosystem.<\/p>\n<p>Relatedly, see how <a href=\"https:\/\/jacar.es\/desarrollo-y-avances-en-inteligencia-artificial\/\">generative AI is changing creative disciplines<\/a> and how it fits with established workflows.<\/p>\n<h2 id=\"conclusion\">Conclusion<\/h2>\n<p>SDXL consolidates open image generation as a competitive alternative to proprietary models. For teams wanting control, reproducibility, or predictable cost, it justifies its hardware cost. For sporadic use or without specific technical requirements, managed models remain the lowest-friction path.<\/p>\n<p>Follow us on jacar.es for more on generative AI applied to image, video, and audio.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Stable Diffusion XL marks a leap in generated-image quality under an open license. What changes vs SD 1.5\/2.1 and when to use each.<\/p>\n","protected":false},"author":1,"featured_media":380,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[24,22],"tags":[56,88,38,87,89,86],"class_list":["post-377","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-herramientas","category-inteligencia-artificial","tag-ia-generativa","tag-imagen-generada","tag-open-source","tag-sdxl","tag-stability-ai","tag-stable-diffusion"],"translation":{"provider":"WPGlobus","version":"3.0.2","language":"en","enabled_languages":["es","en"],"languages":{"es":{"title":true,"content":true,"excerpt":true},"en":{"title":true,"content":true,"excerpt":true}}},"gutentor_comment":0,"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Stable Diffusion XL: Powerful Open Image Generation - Jacar<\/title>\n<meta name=\"description\" content=\"Stability AI&#039;s Stable Diffusion XL: architecture, requirements, comparison with Midjourney and DALL-E 3, and recommended production workflow.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/jacar.es\/stable-diffusion-xl\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Stable Diffusion XL: Powerful Open Image Generation - Jacar\" \/>\n<meta property=\"og:description\" content=\"Stability AI&#039;s Stable Diffusion XL: architecture, requirements, comparison with Midjourney and DALL-E 3, and recommended production workflow.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/jacar.es\/stable-diffusion-xl\/\" \/>\n<meta property=\"og:site_name\" content=\"Jacar\" \/>\n<meta property=\"article:published_time\" content=\"2023-07-07T10:00:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-04-19T18:32:28+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\/wp-content\/uploads\/2023\/07\/19200341\/jwp-1086094-11339.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"800\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"javi\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"javi\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/jacar.es\\\/stable-diffusion-xl\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/stable-diffusion-xl\\\/\"},\"author\":{\"name\":\"javi\",\"@id\":\"https:\\\/\\\/jacar.es\\\/#\\\/schema\\\/person\\\/54a7f7b4224b38fafc9866eb3e614208\"},\"headline\":\"Stable Diffusion XL: Powerful Open Image Generation\",\"datePublished\":\"2023-07-07T10:00:00+00:00\",\"dateModified\":\"2026-04-19T18:32:28+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/stable-diffusion-xl\\\/\"},\"wordCount\":1401,\"publisher\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/stable-diffusion-xl\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/19200341\\\/jwp-1086094-11339.jpg\",\"keywords\":[\"ia generativa\",\"imagen generada\",\"open-source\",\"sdxl\",\"stability ai\",\"stable diffusion\"],\"articleSection\":[\"Herramientas\",\"Inteligencia Artificial\"],\"inLanguage\":\"en-US\"},{\"@type\":[\"WebPage\",\"ItemPage\"],\"@id\":\"https:\\\/\\\/jacar.es\\\/stable-diffusion-xl\\\/\",\"url\":\"https:\\\/\\\/jacar.es\\\/stable-diffusion-xl\\\/\",\"name\":\"Stable Diffusion XL: Powerful Open Image Generation - Jacar\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/stable-diffusion-xl\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/stable-diffusion-xl\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/19200341\\\/jwp-1086094-11339.jpg\",\"datePublished\":\"2023-07-07T10:00:00+00:00\",\"dateModified\":\"2026-04-19T18:32:28+00:00\",\"description\":\"Stability AI's Stable Diffusion XL: architecture, requirements, comparison with Midjourney and DALL-E 3, and recommended production workflow.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/stable-diffusion-xl\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/jacar.es\\\/stable-diffusion-xl\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/jacar.es\\\/stable-diffusion-xl\\\/#primaryimage\",\"url\":\"https:\\\/\\\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/19200341\\\/jwp-1086094-11339.jpg\",\"contentUrl\":\"https:\\\/\\\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/19200341\\\/jwp-1086094-11339.jpg\",\"width\":1200,\"height\":800,\"caption\":\"Imagen generada por IA con paisajes digitales\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/jacar.es\\\/stable-diffusion-xl\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Portada\",\"item\":\"https:\\\/\\\/jacar.es\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Stable Diffusion XL: generaci\u00f3n de im\u00e1genes abierta y potente\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/jacar.es\\\/#website\",\"url\":\"https:\\\/\\\/jacar.es\\\/\",\"name\":\"Jacar\",\"description\":\"Passion for Technology\",\"publisher\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/jacar.es\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/jacar.es\\\/#organization\",\"name\":\"Jacar\",\"url\":\"https:\\\/\\\/jacar.es\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/jacar.es\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/jacar.es\\\/wp-content\\\/uploads\\\/2020\\\/09\\\/favicon.png\",\"contentUrl\":\"https:\\\/\\\/jacar.es\\\/wp-content\\\/uploads\\\/2020\\\/09\\\/favicon.png\",\"width\":252,\"height\":229,\"caption\":\"Jacar\"},\"image\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/in\\\/javiercanetearroyo\\\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/jacar.es\\\/#\\\/schema\\\/person\\\/54a7f7b4224b38fafc9866eb3e614208\",\"name\":\"javi\",\"sameAs\":[\"https:\\\/\\\/jacar.es\"],\"url\":\"https:\\\/\\\/jacar.es\\\/en\\\/author\\\/javi\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Stable Diffusion XL: Powerful Open Image Generation - Jacar","description":"Stability AI's Stable Diffusion XL: architecture, requirements, comparison with Midjourney and DALL-E 3, and recommended production workflow.","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:\/\/jacar.es\/stable-diffusion-xl\/","og_locale":"en_US","og_type":"article","og_title":"Stable Diffusion XL: Powerful Open Image Generation - Jacar","og_description":"Stability AI's Stable Diffusion XL: architecture, requirements, comparison with Midjourney and DALL-E 3, and recommended production workflow.","og_url":"https:\/\/jacar.es\/stable-diffusion-xl\/","og_site_name":"Jacar","article_published_time":"2023-07-07T10:00:00+00:00","article_modified_time":"2026-04-19T18:32:28+00:00","og_image":[{"width":1200,"height":800,"url":"https:\/\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\/wp-content\/uploads\/2023\/07\/19200341\/jwp-1086094-11339.jpg","type":"image\/jpeg"}],"author":"javi","twitter_card":"summary_large_image","twitter_misc":{"Written by":"javi","Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/jacar.es\/stable-diffusion-xl\/#article","isPartOf":{"@id":"https:\/\/jacar.es\/stable-diffusion-xl\/"},"author":{"name":"javi","@id":"https:\/\/jacar.es\/#\/schema\/person\/54a7f7b4224b38fafc9866eb3e614208"},"headline":"Stable Diffusion XL: Powerful Open Image Generation","datePublished":"2023-07-07T10:00:00+00:00","dateModified":"2026-04-19T18:32:28+00:00","mainEntityOfPage":{"@id":"https:\/\/jacar.es\/stable-diffusion-xl\/"},"wordCount":1401,"publisher":{"@id":"https:\/\/jacar.es\/#organization"},"image":{"@id":"https:\/\/jacar.es\/stable-diffusion-xl\/#primaryimage"},"thumbnailUrl":"https:\/\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\/wp-content\/uploads\/2023\/07\/19200341\/jwp-1086094-11339.jpg","keywords":["ia generativa","imagen generada","open-source","sdxl","stability ai","stable diffusion"],"articleSection":["Herramientas","Inteligencia Artificial"],"inLanguage":"en-US"},{"@type":["WebPage","ItemPage"],"@id":"https:\/\/jacar.es\/stable-diffusion-xl\/","url":"https:\/\/jacar.es\/stable-diffusion-xl\/","name":"Stable Diffusion XL: Powerful Open Image Generation - Jacar","isPartOf":{"@id":"https:\/\/jacar.es\/#website"},"primaryImageOfPage":{"@id":"https:\/\/jacar.es\/stable-diffusion-xl\/#primaryimage"},"image":{"@id":"https:\/\/jacar.es\/stable-diffusion-xl\/#primaryimage"},"thumbnailUrl":"https:\/\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\/wp-content\/uploads\/2023\/07\/19200341\/jwp-1086094-11339.jpg","datePublished":"2023-07-07T10:00:00+00:00","dateModified":"2026-04-19T18:32:28+00:00","description":"Stability AI's Stable Diffusion XL: architecture, requirements, comparison with Midjourney and DALL-E 3, and recommended production workflow.","breadcrumb":{"@id":"https:\/\/jacar.es\/stable-diffusion-xl\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/jacar.es\/stable-diffusion-xl\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/jacar.es\/stable-diffusion-xl\/#primaryimage","url":"https:\/\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\/wp-content\/uploads\/2023\/07\/19200341\/jwp-1086094-11339.jpg","contentUrl":"https:\/\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\/wp-content\/uploads\/2023\/07\/19200341\/jwp-1086094-11339.jpg","width":1200,"height":800,"caption":"Imagen generada por IA con paisajes digitales"},{"@type":"BreadcrumbList","@id":"https:\/\/jacar.es\/stable-diffusion-xl\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Portada","item":"https:\/\/jacar.es\/"},{"@type":"ListItem","position":2,"name":"Stable Diffusion XL: generaci\u00f3n de im\u00e1genes abierta y potente"}]},{"@type":"WebSite","@id":"https:\/\/jacar.es\/#website","url":"https:\/\/jacar.es\/","name":"Jacar","description":"Passion for Technology","publisher":{"@id":"https:\/\/jacar.es\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/jacar.es\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/jacar.es\/#organization","name":"Jacar","url":"https:\/\/jacar.es\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/jacar.es\/#\/schema\/logo\/image\/","url":"https:\/\/jacar.es\/wp-content\/uploads\/2020\/09\/favicon.png","contentUrl":"https:\/\/jacar.es\/wp-content\/uploads\/2020\/09\/favicon.png","width":252,"height":229,"caption":"Jacar"},"image":{"@id":"https:\/\/jacar.es\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.linkedin.com\/in\/javiercanetearroyo\/"]},{"@type":"Person","@id":"https:\/\/jacar.es\/#\/schema\/person\/54a7f7b4224b38fafc9866eb3e614208","name":"javi","sameAs":["https:\/\/jacar.es"],"url":"https:\/\/jacar.es\/en\/author\/javi\/"}]}},"_links":{"self":[{"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/posts\/377","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/comments?post=377"}],"version-history":[{"count":1,"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/posts\/377\/revisions"}],"predecessor-version":[{"id":389,"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/posts\/377\/revisions\/389"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/media\/380"}],"wp:attachment":[{"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/media?parent=377"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/categories?post=377"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/tags?post=377"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}