{"id":2914,"date":"2026-04-08T10:53:36","date_gmt":"2026-04-08T10:53:36","guid":{"rendered":"https:\/\/www.cutout.pro\/learn\/?p=2914"},"modified":"2026-04-24T10:13:00","modified_gmt":"2026-04-24T10:13:00","slug":"blog-what-is-happyhorse-1-0","status":"publish","type":"post","link":"https:\/\/www.cutout.pro\/learn\/blog-what-is-happyhorse-1-0\/","title":{"rendered":"What Is HappyHorse-1.0? The Mystery #1 AI Video Model"},"content":{"rendered":"\n<div class=\"wp-block-rank-math-toc-block\" id=\"rank-math-toc\"><h2>Table of Contents<\/h2><nav><ul><li><a href=\"#what-artificial-analysis-has-actually-confirmed\">What Artificial Analysis has actually confirmed<\/a><\/li><li><a href=\"#what-multiple-sites-claim-and-what-i-cant-verify-yet\">What multiple sites claim \u2014 and what I can&#8217;t verify yet<\/a><\/li><li><a href=\"#why-i-2-v-users-should-actually-pay-attention\">Why I2V users should actually pay attention<\/a><\/li><li><a href=\"#known-limits-and-open-questions\">Known limits and open questions<\/a><\/li><li><a href=\"#faq\">FAQ<\/a><ul><li><a href=\"#is-happy-horse-1-0-made-by-byte-dance-deep-seek-or-tencent\">Is HappyHorse-1.0 made by ByteDance, DeepSeek, or Tencent?<\/a><\/li><li><a href=\"#can-i-use-happy-horse-1-0-for-commercial-video-today\">Can I use HappyHorse-1.0 for commercial video today?<\/a><\/li><li><a href=\"#does-input-image-quality-affect-happy-horse-output\">Does input image quality affect HappyHorse output?<\/a><\/li><li><a href=\"#how-often-do-artificial-analysis-elo-scores-change\">How often do Artificial Analysis Elo scores change?<\/a><\/li><\/ul><\/li><\/ul><\/nav><\/div>\n\n\n\n<figure class=\"wp-block-gallery has-nested-images columns-default is-cropped wp-block-gallery-1 is-layout-flex wp-block-gallery-is-layout-flex\">\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"595\" data-id=\"2920\" src=\"https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-28-1024x595.png\" alt=\"\" class=\"wp-image-2920\" srcset=\"https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-28-1024x595.png 1024w, https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-28-300x174.png 300w, https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-28-768x446.png 768w, https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-28.png 1387w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n<\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">I&#8217;m Camille. Last week I was doing what I do on slow mornings \u2014 scrolling through the Artificial Analysis Video Arena, checking which models had moved up or down. A name I&#8217;d never seen was sitting at the very top of both text-to-video and image-to-video. <strong>HappyHorse-1.0.<\/strong> No team page I could open. No paper. Links that said &#8220;coming soon.&#8221;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">If you make product videos, brand content, or any kind of AI-generated visuals for a living, and a pseudonymous model beating Seedance 2.0 and Kling 3.0 sounds like it deserves a closer look \u2014 same. This piece is a grounded walkthrough of what&#8217;s actually confirmed, what&#8217;s only claimed on marketing pages, and what the I2V numbers might mean if you work with reference images every day.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Let&#8217;s separate the signal from the rumor.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"what-artificial-analysis-has-actually-confirmed\">What Artificial Analysis has actually confirmed<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">The one hard fact we have is this: on April 7, 2026, <a href=\"https:\/\/x.com\/ArtificialAnlys\/status\/2041591989083500933\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">Artificial Analysis announced on X<\/a> that they had added a new model to their Video Arena, using the exact word <strong>&#8220;pseudonymous.&#8221;<\/strong> That word matters. It means the submission came in without a verifiable team, organization, or paper attached. No marketing, no lab self-reporting \u2014 just a model generating outputs that blind users kept voting for.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The current positions, which I just re-checked on the <a href=\"https:\/\/artificialanalysis.ai\/video\/leaderboard\/text-to-video\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">Artificial Analysis Text-to-Video leaderboard<\/a> and <a href=\"https:\/\/artificialanalysis.ai\/video\/leaderboard\/image-to-video\" target=\"_blank\" rel=\"noopener\">Image-to-Video leaderboard<\/a>:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>T2V, no audio \u2014 HappyHorse-1.0 at Elo ~1364<\/strong>, ahead of Dreamina Seedance 2.0 at 1269 and Kling 3.0 Pro at 1244.<\/li>\n\n\n\n<li><strong>I2V, no audio \u2014 HappyHorse-1.0 at Elo ~1399<\/strong>, leading the entire board.<\/li>\n\n\n\n<li><strong>With audio \u2014 Seedance 2.0 edges ahead in both audio categories<\/strong>, by very slim margins.<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">Quick honesty note: these scores update live. By the time you read this, they will have shifted. Elo for newly added models is more volatile than established ones, and nobody has published HappyHorse&#8217;s vote sample count. Seedance has 7,500+ votes behind its number. Past me would have taken a two-day-old leaderboard reading as gospel \u2014 current me knows better.<\/p>\n\n\n\n<figure class=\"wp-block-gallery has-nested-images columns-default is-cropped wp-block-gallery-2 is-layout-flex wp-block-gallery-is-layout-flex\">\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"590\" data-id=\"3049\" src=\"https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-81-1024x590.png\" alt=\"\" class=\"wp-image-3049\" srcset=\"https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-81-1024x590.png 1024w, https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-81-300x173.png 300w, https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-81-768x443.png 768w, https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-81.png 1254w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n<\/figure>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"what-multiple-sites-claim-and-what-i-cant-verify-yet\">What multiple sites claim \u2014 and what I can&#8217;t verify yet<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Here&#8217;s where things get a bit murky. A cluster of sites \u2014 <a href=\"https:\/\/happyhorse-ai.com\/\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">happyhorse-ai.com<\/a> being the most prominent \u2014 describe the same model with the same specs: <strong>a 15-billion-parameter single-stream Transformer, 40 layers, joint video-and-audio generation in one forward pass, 7-language lip-sync, ~38 seconds for a 1080p clip on an H100, fully open sourceunder a commercial-use license.<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Those specs are plausible. They&#8217;re also <strong>unverified<\/strong>. As of publish date, the GitHub and Hugging Face links on those sites still return &#8220;coming soon&#8221; or 404. No public API. No downloadable weights. No documented pricing. A separate marketing claim attributes the team to a group &#8220;formerly of Alibaba&#8217;s Taotian Group, led by Zhang Di (ex-Kling AI),&#8221; which <a href=\"https:\/\/www.morningstar.com\/news\/accesswire\/1158274msn\/happy-horse-10-surges-to-no1-in-pure-visual-quality-on-artificial-analysis-video-arena\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">a Morningstar \/ Access Newswire press piece<\/a> also echoes. Treat that as a claim, not a fact.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Community speculation on X has cycled through WAN 2.7, DeepSeek, Tencent, and most persistently a Sand.ai open-source project called daVinci-MagiHuman, whose specs line up suspiciously well with HappyHorse&#8217;s. Nothing has been officially confirmed. A <a href=\"https:\/\/www.barchart.com\/story\/news\/1307546\/happyhorse-10-introduces-the-truth-behind-the-1-opensource-ai-video-model\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">recent analysis from Barchart<\/a> lays out the attribution question pretty honestly \u2014 the most widely reported theory, not confirmed fact.<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p class=\"wp-block-paragraph\"><strong>Bottom line:<\/strong> the leaderboard numbers are real. The team, the weights, the release timeline \u2014 pending.<\/p>\n<\/blockquote>\n\n\n\n<figure class=\"wp-block-gallery has-nested-images columns-default is-cropped wp-block-gallery-3 is-layout-flex wp-block-gallery-is-layout-flex\">\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"742\" height=\"339\" data-id=\"3050\" src=\"https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-82.png\" alt=\"\" class=\"wp-image-3050\" srcset=\"https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-82.png 742w, https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-82-300x137.png 300w\" sizes=\"auto, (max-width: 742px) 100vw, 742px\" \/><\/figure>\n<\/figure>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"why-i-2-v-users-should-actually-pay-attention\">Why I2V users should actually pay attention<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Here&#8217;s the part that stopped me. <strong>HappyHorse&#8217;s I2V (no audio) Elo of ~1399 is the highest number on the entire board<\/strong>, higher than its own T2V score.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">What that tells me, reading between the lines of blind user votes: when creators upload a reference image and compare two outputs side by side, HappyHorse&#8217;s result wins more often. The model seems to <strong>follow the reference more closely<\/strong> \u2014 subject identity, composition, visual coherence. For anyone making product videos or brand content where the motion absolutely has to respect the source image, reference-following is the metric that matters most. Beautiful motion that drifts from your product shape is useless. Locked-on motion that moves your subject convincingly is worth paying for.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">And here&#8217;s the thing that&#8217;s true for HappyHorse, Seedance, Kling, and every I2V model that comes after: <strong>input image quality sets the ceiling of the output.<\/strong> Dirty edges, leftover halos, compression artifacts \u2014 the model reads all of that as signal and amplifies it into motion flicker. I stepped into this hole already, so you don&#8217;t have to. Before blaming the prompt, check the asset. Mm, that usually saves me an hour.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"known-limits-and-open-questions\">Known limits and open questions<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">A few things worth being honest about before anyone rearranges their pipeline around a ranking:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>No public access under the HappyHorse name<\/strong> as of late April 2026. Third-party demo sites exist but aren&#8217;t the model developer.<\/li>\n\n\n\n<li><strong>Elo scores will shift<\/strong> as vote counts grow. Always recheck the live leaderboard.<\/li>\n\n\n\n<li><strong>Audio is not the leading track.<\/strong> If your workflow needs voiceover, ambient sound, or lip-sync, Seedance 2.0 is a tie or slightly ahead.<\/li>\n\n\n\n<li><strong>Clip length is short<\/strong> \u2014 current outputs are optimized around 5\u20138 seconds.<\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-gallery has-nested-images columns-default is-cropped wp-block-gallery-4 is-layout-flex wp-block-gallery-is-layout-flex\">\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"673\" data-id=\"3051\" src=\"https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-83-1024x673.png\" alt=\"\" class=\"wp-image-3051\" srcset=\"https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-83-1024x673.png 1024w, https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-83-300x197.png 300w, https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-83-768x505.png 768w, https:\/\/www.cutout.pro\/learn\/wp-content\/uploads\/2026\/04\/image-83.png 1127w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n<\/figure>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"faq\">FAQ<\/h2>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"is-happy-horse-1-0-made-by-byte-dance-deep-seek-or-tencent\"><strong>Is HappyHorse-1.0 made by ByteDance, DeepSeek, or Tencent?<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">No evidence of any of those. Artificial Analysis called it &#8220;pseudonymous.&#8221; The most persistent community claim points toward an Alibaba-lineage team, but nothing has been independently verified.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"can-i-use-happy-horse-1-0-for-commercial-video-today\"><strong>Can I use HappyHorse-1.0 for commercial video today?<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Not directly. No public API, no weights, no pricing under the HappyHorse name. Third-party demo sites have their own terms.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"does-input-image-quality-affect-happy-horse-output\"><strong>Does input image quality affect HappyHorse output?<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Yes \u2014 every I2V model amplifies input flaws. Clean edges and high-resolution sources matter more than prompt rewriting. This will be true whenever HappyHorse becomes accessible.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"how-often-do-artificial-analysis-elo-scores-change\"><strong>How often do Artificial Analysis Elo scores change?<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Continuously. A #1 model today can be #3 next week as newer entries collect votes. Always check the live board rather than any article, including this one.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Alright. A model nobody can name is at the top of the most credible video benchmark we have, and the gap between confirmed and claimed is still wide. My take: keep it on your radar, verify before you commit, and don&#8217;t let hype decide your workflow for you.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">See you next time \u2014 may your reference images stay clean.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Previous posts:<\/strong><\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed is-provider-cutout-pro-blog wp-block-embed-cutout-pro-blog\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"a536voN8Qy\"><a href=\"https:\/\/www.cutout.pro\/learn\/blog-seedance-2-0-audio-guide\/\">Seedance 2.0 Audio Guide: Dialogue, SFX, BGM, and Lip Sync Tips<\/a><\/blockquote><iframe loading=\"lazy\" class=\"wp-embedded-content\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"&#8220;Seedance 2.0 Audio Guide: Dialogue, SFX, BGM, and Lip Sync Tips&#8221; &#8212; Cutout.pro  Blog\" src=\"https:\/\/www.cutout.pro\/learn\/blog-seedance-2-0-audio-guide\/embed\/#?secret=l6pdW2Y5ZC#?secret=a536voN8Qy\" data-secret=\"a536voN8Qy\" width=\"500\" height=\"282\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"><\/iframe>\n<\/figure>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed is-provider-cutout-pro-blog wp-block-embed-cutout-pro-blog\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"MIpnoEQ0AY\"><a href=\"https:\/\/www.cutout.pro\/learn\/blog-ai-image-to-video-online\/\">AI Image to Video Online: Turn Any Photo Into a Motion Clip (Free)<\/a><\/blockquote><iframe loading=\"lazy\" class=\"wp-embedded-content\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"&#8220;AI Image to Video Online: Turn Any Photo Into a Motion Clip (Free)&#8221; &#8212; Cutout.pro  Blog\" src=\"https:\/\/www.cutout.pro\/learn\/blog-ai-image-to-video-online\/embed\/#?secret=aU6pb7JN9V#?secret=MIpnoEQ0AY\" data-secret=\"MIpnoEQ0AY\" width=\"500\" height=\"282\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"><\/iframe>\n<\/figure>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed is-provider-cutout-pro-blog wp-block-embed-cutout-pro-blog\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"iniZB3Ee73\"><a href=\"https:\/\/www.cutout.pro\/learn\/blog-seedance-2-0-image-to-video\/\">Seedance 2.0 Image to Video: Turn One Photo Into a Consistent 16s Clip<\/a><\/blockquote><iframe loading=\"lazy\" class=\"wp-embedded-content\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"&#8220;Seedance 2.0 Image to Video: Turn One Photo Into a Consistent 16s Clip&#8221; &#8212; Cutout.pro  Blog\" src=\"https:\/\/www.cutout.pro\/learn\/blog-seedance-2-0-image-to-video\/embed\/#?secret=6ZxdfxtaEp#?secret=iniZB3Ee73\" data-secret=\"iniZB3Ee73\" width=\"500\" height=\"282\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"><\/iframe>\n<\/figure>\n","protected":false},"excerpt":{"rendered":"<p>I&#8217;m Camille. Last week I was doing what I do on slow mornings \u2014 scrolling through the Artificial Analysis Video [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":2920,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","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":"","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-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-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-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-gradient":""}},"ast-content-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-gradient":""},"tablet":{"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-gradient":""},"mobile":{"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-gradient":""}},"footnotes":""},"categories":[25],"tags":[],"class_list":["post-2914","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-news"],"_links":{"self":[{"href":"https:\/\/www.cutout.pro\/learn\/wp-json\/wp\/v2\/posts\/2914","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.cutout.pro\/learn\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.cutout.pro\/learn\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.cutout.pro\/learn\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.cutout.pro\/learn\/wp-json\/wp\/v2\/comments?post=2914"}],"version-history":[{"count":2,"href":"https:\/\/www.cutout.pro\/learn\/wp-json\/wp\/v2\/posts\/2914\/revisions"}],"predecessor-version":[{"id":3052,"href":"https:\/\/www.cutout.pro\/learn\/wp-json\/wp\/v2\/posts\/2914\/revisions\/3052"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.cutout.pro\/learn\/wp-json\/wp\/v2\/media\/2920"}],"wp:attachment":[{"href":"https:\/\/www.cutout.pro\/learn\/wp-json\/wp\/v2\/media?parent=2914"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.cutout.pro\/learn\/wp-json\/wp\/v2\/categories?post=2914"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.cutout.pro\/learn\/wp-json\/wp\/v2\/tags?post=2914"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}