{"id":366,"date":"2026-05-29T03:01:40","date_gmt":"2026-05-29T03:01:40","guid":{"rendered":"https:\/\/convly.ai\/?p=366"},"modified":"2026-06-10T05:05:01","modified_gmt":"2026-06-10T05:05:01","slug":"best-gpus-for-stable-diffusion-2026","status":"publish","type":"post","link":"https:\/\/convly.ai\/it\/best-gpus-for-stable-diffusion-2026\/","title":{"rendered":"The Best GPUs for Stable Diffusion and FLUX in 2026"},"content":{"rendered":"<p>Running Stable Diffusion or FLUX on your own GPU means unlimited, free, private image generation \u2014 no credits, no queues, no per-image cost. The good news for 2026: image generation is far less VRAM-hungry than running large language models, so you don&#8217;t need a flagship card to get a great experience. You just need to choose well.<\/p>\n<p>This guide ranks the best GPUs for local image generation with Stable Diffusion and FLUX.<\/p>\n<div class=\"convly-tldr\">\n<h3>Punti chiave<\/h3>\n<ul>\n<li><strong>Migliore in assoluto:<\/strong> RTX 5090 (32 GB) \u2014 fastest generation and headroom for everything.<\/li>\n<li><strong>Best value:<\/strong> RTX 5070 Ti (16 GB) \u2014 fast, with enough VRAM for FLUX.<\/li>\n<li><strong>Best budget:<\/strong> RTX 5060 Ti 16 GB \u2014 the cheapest comfortable image-gen card.<\/li>\n<li><strong>VRAM target:<\/strong> 12 GB minimum, 16 GB comfortable \u2014 FLUX wants the 16 GB.<\/li>\n<li><strong>NVIDIA strongly preferred<\/strong> for the smoothest tooling experience.<\/li>\n<\/ul>\n<\/div>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_84 counter-flat ez-toc-counter ez-toc-container-direction\">\n<label for=\"ez-toc-cssicon-toggle-item-6a38ba758299d\" class=\"ez-toc-cssicon-toggle-label\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Attiva\/Disattiva<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #000000;color:#000000\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewbox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #000000;color:#000000\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewbox=\"0 0 24 24\" version=\"1.2\" baseprofile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input type=\"checkbox\"  id=\"ez-toc-cssicon-toggle-item-6a38ba758299d\"  aria-label=\"Attiva\/Disattiva\" \/><nav><ul class='ez-toc-list ez-toc-list-level-1' ><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/convly.ai\/it\/best-gpus-for-stable-diffusion-2026\/#What_image_generation_needs_from_a_GPU\" >What image generation needs from a GPU<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/convly.ai\/it\/best-gpus-for-stable-diffusion-2026\/#The_rankings\" >The rankings<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/convly.ai\/it\/best-gpus-for-stable-diffusion-2026\/#Side-by-side_comparison\" >Side-by-side comparison<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/convly.ai\/it\/best-gpus-for-stable-diffusion-2026\/#How_to_choose\" >Come scegliere<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/convly.ai\/it\/best-gpus-for-stable-diffusion-2026\/#A_note_on_VRAM_and_FLUX\" >A note on VRAM and FLUX<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/convly.ai\/it\/best-gpus-for-stable-diffusion-2026\/#Getting_the_most_out_of_your_card\" >Getting the most out of your card<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/convly.ai\/it\/best-gpus-for-stable-diffusion-2026\/#FAQ\" >Domande frequenti<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/convly.ai\/it\/best-gpus-for-stable-diffusion-2026\/#Bottom_line\" >Conclusione<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/convly.ai\/it\/best-gpus-for-stable-diffusion-2026\/#Related_articles\" >Articoli correlati<\/a><\/li><\/ul><\/nav><\/div>\n<h2><span class=\"ez-toc-section\" id=\"What_image_generation_needs_from_a_GPU\"><\/span>What image generation needs from a GPU<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Image generation has a different hardware profile than LLMs:<\/p>\n<ol>\n<li><strong>VRAM<\/strong> \u2014 still important, but the bar is lower. Stable Diffusion runs in modest memory; <strong>FLUX<\/strong>, the larger modern model, is hungrier and is the reason to aim for 16 GB.<\/li>\n<li><strong>Compute speed<\/strong> \u2014 this matters more here than for LLMs. It directly sets how many seconds each image takes, and that adds up fast when you iterate.<\/li>\n<li><strong>CUDA<\/strong> \u2014 the image-generation tooling ecosystem (the popular interfaces, extensions, and nodes) is built around NVIDIA. AMD works but with more friction.<\/li>\n<\/ol>\n<p>The short version: 12 GB gets you running, 16 GB makes FLUX and high resolutions comfortable, and faster compute simply means more images per hour.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"The_rankings\"><\/span>The rankings<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<h3>1. RTX 5090 \u2014 best overall<\/h3>\n<p>The RTX 5090 generates images faster than anything else and its <strong>32 GB of VRAM<\/strong> removes every limit \u2014 high resolutions, FLUX at full quality, big batches, and running other models alongside. It&#8217;s overkill for casual image generation, but for professionals generating at volume, or anyone who also runs LLMs and video, it&#8217;s the no-compromise pick.<\/p>\n<h3>2. RTX 5070 Ti \u2014 best value<\/h3>\n<p>The RTX 5070 Ti is the sweet spot for image generation. Its <strong>16 GB of VRAM<\/strong> comfortably handles FLUX and Stable Diffusion at high resolution, and its strong compute keeps generation times short. For the large majority of people who want a fast, capable local image-generation rig without flagship pricing, this is the card to buy.<\/p>\n<h3>3. RTX 5080 \u2014 fast, if you want the extra speed<\/h3>\n<p>The RTX 5080 also has <strong>16 GB<\/strong> but more compute than the 5070 Ti. For image generation, that means quicker generations at the same memory ceiling. It&#8217;s a fine choice if you generate constantly and value the speed \u2014 but the 5070 Ti delivers most of the experience for less.<\/p>\n<h3>4. RTX 5060 Ti 16 GB \u2014 best budget pick<\/h3>\n<p>The 16 GB RTX 5060 Ti is the best budget option. It&#8217;s not fast, but <strong>16 GB<\/strong> means FLUX and Stable Diffusion both run properly rather than in a cramped, compromised mode. Generations take longer than on higher cards, but for hobbyists and beginners it delivers the full local image-generation experience at the lowest sensible price.<\/p>\n<h3>5. Used RTX 3090 \/ 4070 Ti Super \u2014 value alternatives<\/h3>\n<p>A used <strong>RTX 3090<\/strong> brings 24 GB for a low price \u2014 more VRAM than you strictly need for image generation, but useful if you also run LLMs. A used <strong>RTX 4070 Ti Super<\/strong> (16 GB) is another solid secondhand pick with good speed. Both are smart buys if the price is right.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Side-by-side_comparison\"><\/span>Side-by-side comparison<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<table class=\"convly-vs\">\n<thead>\n<tr>\n<th>GPU<\/th>\n<th>VRAM<\/th>\n<th>Image-gen speed<\/th>\n<th>Rough price<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>RTX 5090<\/td>\n<td>32 GB<\/td>\n<td>Il pi\u00f9 veloce<\/td>\n<td>$2,000+<\/td>\n<\/tr>\n<tr>\n<td>RTX 5080<\/td>\n<td>16 GB<\/td>\n<td>Very fast<\/td>\n<td>~$1,000<\/td>\n<\/tr>\n<tr>\n<td>RTX 5070 Ti<\/td>\n<td>16 GB<\/td>\n<td>Veloce<\/td>\n<td>~$750<\/td>\n<\/tr>\n<tr>\n<td>RTX 5060 Ti 16 GB<\/td>\n<td>16 GB<\/td>\n<td>Moderato<\/td>\n<td>~$430<\/td>\n<\/tr>\n<tr>\n<td>Used RTX 3090<\/td>\n<td>24 GB<\/td>\n<td>Veloce<\/td>\n<td>~$700\u2013900<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2><span class=\"ez-toc-section\" id=\"How_to_choose\"><\/span>Come scegliere<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ul>\n<li><strong>You generate professionally or also run LLMs\/video:<\/strong> RTX 5090.<\/li>\n<li><strong>You want the best value for a dedicated image rig:<\/strong> RTX 5070 Ti.<\/li>\n<li><strong>You generate constantly and want maximum speed in 16 GB:<\/strong> RTX 5080.<\/li>\n<li><strong>You&#8217;re a hobbyist on a budget:<\/strong> RTX 5060 Ti 16 GB.<\/li>\n<li><strong>You want extra VRAM cheaply:<\/strong> a used RTX 3090.<\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"A_note_on_VRAM_and_FLUX\"><\/span>A note on VRAM and FLUX<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>If you&#8217;re choosing between a 12 GB and a 16 GB card, get the 16 GB. Stable Diffusion&#8217;s older models are content with 12 GB, but FLUX \u2014 the higher-quality modern model most people will want to use \u2014 is noticeably more comfortable with 16 GB. That extra memory also unlocks higher resolutions and bigger batches. 16 GB is the spec to target.<\/p>\n<p><!--ai-enriched--><\/p>\n<h2><span class=\"ez-toc-section\" id=\"Getting_the_most_out_of_your_card\"><\/span>Getting the most out of your card<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The GPU you buy sets a ceiling on performance, but the software you run decides how close you get to it. Two people with identical RTX 5070 Ti cards can see very different iterations-per-second depending on a handful of settings. Before you spend more on hardware, make sure you are not leaving free speed on the table.<\/p>\n<p><strong>Pick the right attention backend.<\/strong> The attention mechanism is where most diffusion compute goes, and you usually have a choice. The default scaled dot-product attention (SDPA) in PyTorch is the safe option \u2014 broadly compatible and enabled out of the box. xFormers is a long-standing alternative that trims memory use. The newer option, <strong>SageAttention<\/strong>, uses 8-bit attention and is meaningfully faster than both on modern cards \u2014 it has been validated on FLUX and Stable Diffusion 3.5, and the gains are largest on a 50-series GPU. The trade-off is a tiny approximation in the attention math, which almost never shows up in the final image.<\/p>\n<p><strong>Match precision to your VRAM, not your ego.<\/strong> Running FLUX.1 dev at full bf16 wants roughly 24 GB. Drop to an FP8 or Q8 GGUF build and the same model fits comfortably in 12\u201315 GB with image quality that is very hard to tell apart. A Q4 GGUF squeezes FLUX into 6\u20138 GB, which is what makes 12 GB cards viable \u2014 but Q4 is the practical floor, and degradation tends to surface first in hands, faces, and fine text. For serious output, Q8 or FP8 is the sweet spot; reach for Q4 only when VRAM forces your hand.<\/p>\n<p><strong>Use TensorRT with eyes open.<\/strong> NVIDIA&#8217;s TensorRT can roughly double throughput by compiling a model into an optimized engine. The catch is real: engines are built per resolution and per model, the build itself takes minutes, and historically they have been awkward with LoRAs and ControlNet (ControlNet support has since improved, but stacking LoRAs still multiplies the engines you have to bake). If your workflow is a fixed pipeline cranking out many images at one size, TensorRT is excellent. If you swap LoRAs and resolutions constantly, the rebuild friction usually is not worth it.<\/p>\n<ul>\n<li><strong>Keep drivers current<\/strong> \u2014 backend support and FP8 kernels improve with new releases.<\/li>\n<li><strong>Enable tiled VAE decoding<\/strong> on tighter-VRAM cards to avoid out-of-memory errors at high resolution.<\/li>\n<li><strong>Batch when you can<\/strong> \u2014 generating several images at once uses the GPU more efficiently than one at a time.<\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"FAQ\"><\/span>Domande frequenti<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<h3>What is the best GPU for Stable Diffusion in 2026?<\/h3>\n<p>The RTX 5090 (32 GB) is the fastest and most capable, but it&#8217;s more than most people need. The RTX 5070 Ti (16 GB) is the best-value choice \u2014 fast, with enough VRAM for FLUX and Stable Diffusion \u2014 and the RTX 5060 Ti 16 GB is the best budget pick.<\/p>\n<h3>How much VRAM do I need for Stable Diffusion and FLUX?<\/h3>\n<p>12 GB is the practical minimum and runs Stable Diffusion well. 16 GB is the comfortable target, especially for FLUX, which is larger and more memory-hungry than older models. 16 GB also enables higher resolutions and larger batches.<\/p>\n<h3>Is image generation less demanding than running LLMs?<\/h3>\n<p>Yes. Image generation with Stable Diffusion and FLUX needs less VRAM than running large language models, so you don&#8217;t need a flagship card for a great experience. Compute speed matters more here, since it directly sets how long each image takes.<\/p>\n<h3>Can I run Stable Diffusion on an AMD GPU?<\/h3>\n<p>You can, but with more friction. The popular image-generation interfaces and extensions are built around NVIDIA&#8217;s CUDA ecosystem. AMD cards work and have improved, but for the smoothest experience with the widest tool support, NVIDIA is strongly preferred.<\/p>\n<h3>Is a used RTX 3090 good for image generation?<\/h3>\n<p>Yes. A used RTX 3090 offers 24 GB of VRAM and good speed at a low price. That&#8217;s more memory than image generation strictly requires, but it&#8217;s a smart buy if you also run large language models or want headroom \u2014 and the value is excellent.<\/p>\n<h3>Is FLUX slower to generate than SDXL on the same GPU?<\/h3>\n<p>Yes. FLUX is a much larger model \u2014 around 12 billion parameters versus SDXL&#8217;s 3.5 billion \u2014 so each image takes longer and demands more VRAM on identical hardware. The quality is a step up, but if speed is your priority, for rapid iteration or high-volume work, SDXL still generates noticeably faster on the same card. Many people prototype on SDXL and switch to FLUX for final renders.<\/p>\n<h3>Will two GPUs make Stable Diffusion generate images faster?<\/h3>\n<p>Not in any normal setup. The popular tools \u2014 ComfyUI, AUTOMATIC1111, Forge \u2014 cannot split a single generation across two cards, so NVLink or SLI buys you nothing for one image. A second GPU only helps throughput: you can run a separate instance on each card and produce two image streams in parallel. For one job to finish faster, you need a single faster card with more VRAM, not two slower ones.<\/p>\n<h3>Does FP8 quantization hurt image quality compared to Q4?<\/h3>\n<p>FP8 and Q8 are close enough to full precision that most users cannot spot the difference in normal output, which is why they are the recommended setting when your VRAM allows. Q4 saves the most memory and unlocks FLUX on 12 GB cards, but it is the quality floor \u2014 artifacts appear first in hands, faces, and small text. Use FP8 or Q8 when you can fit it, and treat Q4 as a VRAM concession rather than a default.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Bottom_line\"><\/span>Conclusione<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>For local Stable Diffusion and FLUX in 2026, you don&#8217;t need to overspend. The <strong>RTX 5070 Ti<\/strong> is the value sweet spot \u2014 fast, with 16 GB for FLUX \u2014 and covers most people perfectly. The <strong>RTX 5090<\/strong> is the no-limits choice for professionals and multi-workload users, while the <strong>RTX 5060 Ti 16 GB<\/strong> brings the full experience to a budget.<\/p>\n<p>Target 16 GB of VRAM on an NVIDIA card, and you&#8217;ll have unlimited, free, private image generation that pays for itself the moment you stop buying credits.<\/p>\n<p><!--related-block--><\/p>\n<div class=\"convly-related\">\n<h2><span class=\"ez-toc-section\" id=\"Related_articles\"><\/span>Articoli correlati<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ul>\n<li><a href=\"https:\/\/convly.ai\/it\/rtx-pro-6000-vs-rtx-5090-for-ai-2026\/\">RTX Pro 6000 Blackwell contro RTX 5090 per l\u2019IA nel 2026: quando giustifica un sovrapprezzo di 5.500 dollari avere 96 GB di VRAM?<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/it\/rtx-5070-vs-rtx-5080-for-ai-2026\/\">RTX 5070 contro RTX 5080 per l\u2019IA nel 2026: vale la pena pagare 450 dollari in pi\u00f9 per passare a 16 GB?<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/it\/best-gpus-for-video-generation-2026\/\">The Best GPUs for AI Video Generation in 2026<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/it\/best-gpus-for-llm-fine-tuning-2026\/\">Le migliori GPU per il fine-tuning di LLM a casa nel 2026<\/a><\/li>\n<\/ul>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>The best GPUs for running Stable Diffusion and FLUX locally in 2026, ranked for VRAM, speed, and value \u2014 with a clear pick for every budget.<\/p>","protected":false},"author":1,"featured_media":541,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[248],"tags":[549,546,547,548,251],"class_list":["post-366","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-gpus","tag-ai-image-gpu","tag-best-gpu-for-stable-diffusion","tag-flux-gpu","tag-image-generation-gpu","tag-rtx-5090"],"_links":{"self":[{"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/posts\/366","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/comments?post=366"}],"version-history":[{"count":3,"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/posts\/366\/revisions"}],"predecessor-version":[{"id":975,"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/posts\/366\/revisions\/975"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/media\/541"}],"wp:attachment":[{"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/media?parent=366"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/categories?post=366"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/convly.ai\/it\/wp-json\/wp\/v2\/tags?post=366"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}