{"id":7304,"date":"2026-05-29T16:46:33","date_gmt":"2026-05-29T08:46:33","guid":{"rendered":"https:\/\/crepal.ai\/blog\/?p=7304"},"modified":"2026-05-29T16:46:40","modified_gmt":"2026-05-29T08:46:40","slug":"ltx-2-3-finetunes","status":"publish","type":"post","link":"https:\/\/crepal.ai\/blog\/aivideo\/ltx-2-3-finetunes\/","title":{"rendered":"LTX 2.3 Finetunes: Sulphur 2 and Beyond"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">I&#8217;m Leo \u2014 the person in your group chat who says &#8220;don&#8217;t buy that, waste of money&#8221; or &#8220;this one&#8217;s actually worth it, get on board.&#8221; Two weeks ago someone dropped a side-by-side in the group chat \u2014 same prompt, same seed, LTX base model vs Sulphur 2. The motion handling felt noticeably different. Not night-and-day different, but different enough that I couldn&#8217;t let it go without understanding why. That&#8217;s the short version of how I ended up going deep on <strong>ltx 2.3 finetune<\/strong> variants for the past week.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">This post covers what these community finetunes actually are under the hood, why creators reach for them instead of the base model, what Sulphur 2 specifically delivers (and where it doesn&#8217;t), and what you need to know before running any of this in ComfyUI.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\" \/>\n\n\n\n<h2 id=\"what-ltx-2-3-finetunes-are\" class=\"wp-block-heading\">What LTX 2.3 Finetunes Are<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">LTX Video \u2014 developed by Lightricks and available on <a href=\"https:\/\/huggingface.co\/Lightricks\/LTX-Video\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">their HuggingFace model page<\/a> \u2014 is an open-source text-to-video diffusion model. Version 2.3 is a community-tracked release that improved motion consistency and temporal coherence over earlier iterations.<\/p>\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 decoding=\"async\" width=\"1024\" height=\"443\" data-id=\"7308\" data-src=\"https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-232-1024x443.png\" alt=\"\" class=\"wp-image-7308 lazyload\" data-srcset=\"https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-232-1024x443.png 1024w, https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-232-300x130.png 300w, https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-232-768x332.png 768w, https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-232-1536x665.png 1536w, https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-232-18x8.png 18w, https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-232.png 1678w\" data-sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 1024px; --smush-placeholder-aspect-ratio: 1024\/443;\" \/><\/figure>\n<\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">A finetune is what the community does with that base checkpoint: take it, continue training on a curated dataset, and push its output toward something more specific. Not a full retrain \u2014 more like sending the model back to school for one particular subject. The base model learns broadly; the finetune gets good at a narrower thing.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">In practice, <strong>ltx video 2.3<\/strong> finetunes tend to target:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Specific visual aesthetics \u2014 film grain behavior, color temperature bias, contrast response<\/li>\n\n\n\n<li>Motion style \u2014 how fluid movement reads, how &#8220;cinematic&#8221; vs raw the motion feels<\/li>\n\n\n\n<li>Subject fidelity \u2014 how well the model holds character and object consistency across frames<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">The base model architecture and training approach are documented in the <a href=\"https:\/\/github.com\/Lightricks\/LTX-Video\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">LTX-Video GitHub repository<\/a>. The finetunes live in the community \u2014 primarily on HuggingFace and Civitai \u2014 and that&#8217;s where real differentiation happens.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\" \/>\n\n\n\n<h2 id=\"why-creators-use-finetunes\" class=\"wp-block-heading\">Why Creators Use Finetunes<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Honest answer: because the base model doesn&#8217;t nail a specific look consistently enough out of the box.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">LTX 2.3 base is capable. It&#8217;s also general-purpose, which means it was trained on a wide variety of footage and it averages toward something competent but not always distinctive. If your content needs to read like it was shot in a particular style \u2014 a specific motion language, a particular color temperature, a specific era of filmmaking \u2014 the base model requires heavy prompt engineering to get there, and even then output is inconsistent run-to-run.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">A finetune shifts that average. Instead of prompting against a generic starting point, you start from a checkpoint already biased toward the aesthetic you need. This is where <strong>open source video finetunes<\/strong> have become genuinely useful for creators who know what they&#8217;re going for visually. The community catalog is expanding \u2014 <a href=\"https:\/\/civitai.com\/models?type=Video\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">Civitai&#8217;s video model section<\/a> is a reasonable place to see what&#8217;s actively maintained and getting traction.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The tradeoff nobody mentions enough: finetunes are less flexible. Push them outside their training distribution and you get artifacts. A finetune that&#8217;s excellent for controlled close-up subject shots might fall apart on wide architectural footage with complex motion. Understanding the envelope matters more than it does with the base model.<\/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-full\"><img decoding=\"async\" width=\"621\" height=\"233\" data-id=\"7306\" data-src=\"https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-230.png\" alt=\"\" class=\"wp-image-7306 lazyload\" data-srcset=\"https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-230.png 621w, https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-230-300x113.png 300w, https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-230-18x7.png 18w\" data-sizes=\"auto, (max-width: 621px) 100vw, 621px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 621px; --smush-placeholder-aspect-ratio: 621\/233;\" \/><\/figure>\n<\/figure>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\" \/>\n\n\n\n<h2 id=\"sulphur-2-case-study\" class=\"wp-block-heading\">Sulphur 2 Case Study<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Sulphur 2 is a community finetune built on LTX Video 2.3, specifically tuned for motion quality and subject retention. That&#8217;s the claim. Here&#8217;s what I found when I actually tested it.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">I ran the same prompt set through LTX 2.3 base and Sulphur 2 six times each. The most consistent difference showed up in fast subject movement: base LTX produced temporal flickering around subject edges on panning shots. Sulphur 2 reduced that meaningfully \u2014 not eliminated, but the improvement was consistent rather than a lucky run. Four of six Sulphur 2 tests came out noticeably cleaner. Two were roughly equivalent to base. That&#8217;s the kind of honest number you should apply to any <strong>ltx 2.3 finetune<\/strong> before committing your workflow to it.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Where Sulphur 2 earns its place:<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><tbody><tr><td class=\"has-text-align-center\" data-align=\"center\">Use Case<\/td><td class=\"has-text-align-center\" data-align=\"center\">Sulphur 2 vs Base LTX<\/td><td class=\"has-text-align-center\" data-align=\"center\">Verdict<\/td><\/tr><tr><td>Talking head \/ presenter video<\/td><td>Cleaner subject edges, better frame consistency<\/td><td>Worth the switch<\/td><\/tr><tr><td>Product shots, controlled motion<\/td><td>Better retention across frames<\/td><td>Worth the switch<\/td><\/tr><tr><td>Complex multi-subject scenes<\/td><td>Competing retention biases cause artifacts<\/td><td>Stick with base<\/td><\/tr><tr><td>Wide environmental shots<\/td><td>Marginal difference<\/td><td>Coin flip<\/td><\/tr><tr><td>Heavy stylistic prompt work<\/td><td>Finetune bias fights the prompt<\/td><td>Base gives more control<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">The pattern: Sulphur 2 wins when the scene is controlled and the subject is the clear anchor. It loses when complexity fights the model&#8217;s narrower training.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">One thing worth flagging \u2014 community finetunes iterate. The version I tested may not be what&#8217;s available when you read this. Check the release notes before you build a whole workflow around a specific generation&#8217;s behavior. This applies to any <strong>ltx 2.3 finetunes<\/strong>, not just this one.<\/p>\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-large\"><img decoding=\"async\" width=\"1024\" height=\"418\" data-id=\"7307\" data-src=\"https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-231-1024x418.png\" alt=\"\" class=\"wp-image-7307 lazyload\" data-srcset=\"https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-231-1024x418.png 1024w, https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-231-300x122.png 300w, https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-231-768x313.png 768w, https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-231-1536x627.png 1536w, https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-231-18x7.png 18w, https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-231.png 1802w\" data-sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 1024px; --smush-placeholder-aspect-ratio: 1024\/418;\" \/><\/figure>\n<\/figure>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\" \/>\n\n\n\n<h2 id=\"compatibility\" class=\"wp-block-heading\">Compatibility<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">This is where <strong>ltx 2.3 comfyui<\/strong> setup matters. <a href=\"https:\/\/github.com\/comfyanonymous\/ComfyUI\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">ComfyUI<\/a> is the standard environment for running LTX Video workflows locally or on cloud instances. LTX-specific custom nodes handle model loading, conditioning, and sampling more reliably than generic diffusion nodes \u2014 you want to use them.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Three things to verify before you start:<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Node currency.<\/strong> LTX 2.3 finetunes require the correct ComfyUI LTX nodes, current version. <a href=\"https:\/\/github.com\/ltdrdata\/ComfyUI-Manager\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">ComfyUI-Manager<\/a> is the fastest way to check and update \u2014 a stale node version produces either broken output or silent failures, and neither is fun to debug mid-project.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>VRAM requirements.<\/strong> LTX 2.3 is not a lightweight model. Rough guidance:<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><tbody><tr><td class=\"has-text-align-center\" data-align=\"center\">VRAM<\/td><td class=\"has-text-align-center\" data-align=\"center\">Expectation<\/td><\/tr><tr><td>8 GB<\/td><td>Runs with quality and resolution compromises<\/td><\/tr><tr><td>12 GB<\/td><td>Workable at moderate resolution<\/td><\/tr><tr><td>16 GB+<\/td><td>Consistent output, full resolution<\/td><\/tr><tr><td>24 GB<\/td><td>Headroom for longer clips and batch work<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">Finetunes don&#8217;t change the VRAM floor, but some Sulphur 2 configurations at higher resolutions push toward the ceiling. Know your hardware before queuing a large batch.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Sampler settings.<\/strong> Community finetunes sometimes come with specific sampler and step recommendations that differ from base model defaults. Check the model release notes before assuming your LTX base settings transfer cleanly. Usually it&#8217;s a minor tweak; occasionally it&#8217;s not.<\/p>\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-full\"><img decoding=\"async\" width=\"628\" height=\"232\" data-id=\"7305\" data-src=\"https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-229.png\" alt=\"\" class=\"wp-image-7305 lazyload\" data-srcset=\"https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-229.png 628w, https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-229-300x111.png 300w, https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/image-229-18x7.png 18w\" data-sizes=\"auto, (max-width: 628px) 100vw, 628px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 628px; --smush-placeholder-aspect-ratio: 628\/232;\" \/><\/figure>\n<\/figure>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\" \/>\n\n\n\n<h2 id=\"faq\" class=\"wp-block-heading\">FAQ<\/h2>\n\n\n\n<h3 id=\"what-are-ltx-2-3-finetunes\" class=\"wp-block-heading\">What are LTX 2.3 finetunes?<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Community-trained checkpoints built on top of the LTX Video 2.3 base model. The training continues from the base checkpoint using curated datasets, pushing output toward a specific aesthetic, motion style, or quality characteristic. They share the base architecture and run in the same environment \u2014 the difference is where the model&#8217;s learned biases land.<\/p>\n\n\n\n<h3 id=\"how-is-sulphur-2-related-to-ltx-2-3\" class=\"wp-block-heading\">How is Sulphur 2 related to LTX 2.3?<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Sulphur 2 is a community finetune built directly on the LTX Video 2.3 checkpoint, tuned specifically for motion quality and subject consistency. The underlying model is still LTX 2.3; what&#8217;s changed is the model&#8217;s defaults have been shifted toward smoother, more controlled movement. It&#8217;s one of the more discussed <strong>ltx 2.3 finetune<\/strong> releases in the community right now, though not the only one worth knowing about.<\/p>\n\n\n\n<h3 id=\"do-ltx-2-3-finetunes-work-in-comfyui\" class=\"wp-block-heading\">Do LTX 2.3 finetunes work in ComfyUI?<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Yes, with the right nodes installed and current. <strong>Ltx 2.3 comfyui<\/strong> workflows load finetunes the same way they load the base model \u2014 you&#8217;re largely just swapping the checkpoint file. The LTX-specific nodes handle the rest. ComfyUI-Manager makes it easy to confirm you have the right node versions before you spend time debugging a workflow that&#8217;s actually a dependency problem.<\/p>\n\n\n\n<h3 id=\"when-should-creators-use-a-finetune-instead-of-the-base-model\" class=\"wp-block-heading\">When should creators use a finetune instead of the base model?<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">When you have a clear target aesthetic and the base model requires heavy, inconsistent prompting to get there. A finetune is a faster route to a specific visual output; the base model is more flexible across varied content. If you&#8217;re producing high-volume content in a consistent style, a finetune built for that style saves per-generation prompt engineering time. If your content varies widely in style and subject matter, the base model&#8217;s generality serves you better \u2014 finetunes trade flexibility for consistency, and that tradeoff only makes sense when you actually want the consistency.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">There are a handful of smaller <strong>ltx 2.3 finetune<\/strong> releases that don&#8217;t get as much attention as Sulphur 2 but are doing interesting things \u2014 particularly around grain and color grading behavior. I&#8217;ll run those properly before writing them up. If you&#8217;re already running Sulphur 2 in production and have settled on sampler settings that work well, drop them in the comments. Specifically curious what step counts people are landing on for the motion quality sweet spot.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\" \/>\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-crepal-content-center wp-block-embed-crepal-content-center\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"4wj1Ivx01x\"><a href=\"https:\/\/crepal.ai\/blog\/aivideo\/aivideo-happyhorse-1-0-api\/\">HappyHorse 1.0 API: Access, Pricing &amp; How to Use It<\/a><\/blockquote><iframe class=\"wp-embedded-content lazyload\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"\u300a HappyHorse 1.0 API: Access, Pricing &amp; How to Use It \u300b\u2014CrePal Content Center\" data-src=\"https:\/\/crepal.ai\/blog\/aivideo\/aivideo-happyhorse-1-0-api\/embed\/#?secret=7U77G5mdRK#?secret=4wj1Ivx01x\" data-secret=\"4wj1Ivx01x\" width=\"600\" height=\"338\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" data-load-mode=\"1\"><\/iframe>\n<\/div><\/figure>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed is-provider-crepal-content-center wp-block-embed-crepal-content-center\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"7asmLgB6Qf\"><a href=\"https:\/\/crepal.ai\/blog\/aivideo\/aivideo-happyhorse-vs-kling-3-0\/\">HappyHorse vs Kling 3.0: Which AI Video Model Wins?<\/a><\/blockquote><iframe class=\"wp-embedded-content lazyload\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"\u300a HappyHorse vs Kling 3.0: Which AI Video Model Wins? \u300b\u2014CrePal Content Center\" data-src=\"https:\/\/crepal.ai\/blog\/aivideo\/aivideo-happyhorse-vs-kling-3-0\/embed\/#?secret=vwuqAgGgI6#?secret=7asmLgB6Qf\" data-secret=\"7asmLgB6Qf\" width=\"600\" height=\"338\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" data-load-mode=\"1\"><\/iframe>\n<\/div><\/figure>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed is-provider-crepal-content-center wp-block-embed-crepal-content-center\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"is7d6jMPCf\"><a href=\"https:\/\/crepal.ai\/blog\/aivideo\/aivideo-image-to-kiss-video-ai-tutorial\/\">How to Create Kiss Scene Videos with Image to Video AI<\/a><\/blockquote><iframe class=\"wp-embedded-content lazyload\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"\u300a How to Create Kiss Scene Videos with Image to Video AI \u300b\u2014CrePal Content Center\" data-src=\"https:\/\/crepal.ai\/blog\/aivideo\/aivideo-image-to-kiss-video-ai-tutorial\/embed\/#?secret=Zyl6XtWbEX#?secret=is7d6jMPCf\" data-secret=\"is7d6jMPCf\" width=\"600\" height=\"338\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" data-load-mode=\"1\"><\/iframe>\n<\/div><\/figure>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed is-provider-crepal-content-center wp-block-embed-crepal-content-center\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"AFQ35kQ178\"><a href=\"https:\/\/crepal.ai\/blog\/aivideo\/aivideo-best-ai-tools-ugc-video-content\/\">Best AI Tools for UGC Video Content Creation in 2026<\/a><\/blockquote><iframe class=\"wp-embedded-content lazyload\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"\u300a Best AI Tools for UGC Video Content Creation in 2026 \u300b\u2014CrePal Content Center\" data-src=\"https:\/\/crepal.ai\/blog\/aivideo\/aivideo-best-ai-tools-ugc-video-content\/embed\/#?secret=aZqIgP78Aa#?secret=AFQ35kQ178\" data-secret=\"AFQ35kQ178\" width=\"600\" height=\"338\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" data-load-mode=\"1\"><\/iframe>\n<\/div><\/figure>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed is-provider-crepal-content-center wp-block-embed-crepal-content-center\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"xBjVLhqi2h\"><a href=\"https:\/\/crepal.ai\/blog\/aivideo\/aivideo-text-to-video-leaderboard-2026\/\">Text to Video AI Leaderboard 2026: Best Models Ranked<\/a><\/blockquote><iframe class=\"wp-embedded-content lazyload\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"\u300a Text to Video AI Leaderboard 2026: Best Models Ranked \u300b\u2014CrePal Content Center\" data-src=\"https:\/\/crepal.ai\/blog\/aivideo\/aivideo-text-to-video-leaderboard-2026\/embed\/#?secret=uJNKD4aVwp#?secret=xBjVLhqi2h\" data-secret=\"xBjVLhqi2h\" width=\"600\" height=\"338\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" data-load-mode=\"1\"><\/iframe>\n<\/div><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>I&#8217;m Leo \u2014 the person in your group chat who says &#8220;don&#8217;t buy that, waste of money&#8221; or &#8220;this one&#8217;s actually worth it, get on board.&#8221; Two weeks ago someone dropped a side-by-side in the group chat \u2014 same prompt, same seed, LTX base model vs Sulphur 2. The motion handling felt noticeably different. Not [&hellip;]<\/p>\n","protected":false},"author":10,"featured_media":7309,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_gspb_post_css":"","_uag_custom_page_level_css":"","footnotes":""},"categories":[8],"tags":[],"class_list":["post-7304","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-aivideo"],"blocksy_meta":[],"uagb_featured_image_src":{"full":["https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/clean_Gemini_Generated_Image_2e0iiw2e0iiw2e0i.jpg",1376,768,false],"thumbnail":["https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/clean_Gemini_Generated_Image_2e0iiw2e0iiw2e0i-150x150.jpg",150,150,true],"medium":["https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/clean_Gemini_Generated_Image_2e0iiw2e0iiw2e0i-300x167.jpg",300,167,true],"medium_large":["https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/clean_Gemini_Generated_Image_2e0iiw2e0iiw2e0i-768x429.jpg",768,429,true],"large":["https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/clean_Gemini_Generated_Image_2e0iiw2e0iiw2e0i-1024x572.jpg",1024,572,true],"1536x1536":["https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/clean_Gemini_Generated_Image_2e0iiw2e0iiw2e0i.jpg",1376,768,false],"2048x2048":["https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/clean_Gemini_Generated_Image_2e0iiw2e0iiw2e0i.jpg",1376,768,false],"trp-custom-language-flag":["https:\/\/crepal.ai\/blog\/wp-content\/uploads\/2026\/05\/clean_Gemini_Generated_Image_2e0iiw2e0iiw2e0i-18x10.jpg",18,10,true]},"uagb_author_info":{"display_name":"Leo","author_link":"https:\/\/crepal.ai\/blog\/author\/leo\/"},"uagb_comment_info":0,"uagb_excerpt":"I&#8217;m Leo \u2014 the person in your group chat who says &#8220;don&#8217;t buy that, waste of money&#8221; or &#8220;this one&#8217;s actually worth it, get on board.&#8221; Two weeks ago someone dropped a side-by-side in the group chat \u2014 same prompt, same seed, LTX base model vs Sulphur 2. The motion handling felt noticeably different. Not&hellip;","_links":{"self":[{"href":"https:\/\/crepal.ai\/blog\/wp-json\/wp\/v2\/posts\/7304","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/crepal.ai\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/crepal.ai\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/crepal.ai\/blog\/wp-json\/wp\/v2\/users\/10"}],"replies":[{"embeddable":true,"href":"https:\/\/crepal.ai\/blog\/wp-json\/wp\/v2\/comments?post=7304"}],"version-history":[{"count":1,"href":"https:\/\/crepal.ai\/blog\/wp-json\/wp\/v2\/posts\/7304\/revisions"}],"predecessor-version":[{"id":7310,"href":"https:\/\/crepal.ai\/blog\/wp-json\/wp\/v2\/posts\/7304\/revisions\/7310"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/crepal.ai\/blog\/wp-json\/wp\/v2\/media\/7309"}],"wp:attachment":[{"href":"https:\/\/crepal.ai\/blog\/wp-json\/wp\/v2\/media?parent=7304"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/crepal.ai\/blog\/wp-json\/wp\/v2\/categories?post=7304"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/crepal.ai\/blog\/wp-json\/wp\/v2\/tags?post=7304"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}