<div data-type="blurb" data-id="229">Comfy Manager is SLOW to upload. sometimes a day or so. If you get ANY missing nodes, just get them from my repo Here: <a target="_blank" rel="ugc" href="https://github.com/lonecatone23">https://github.com/lonecatone23</a> All LC Notes now translate to the following:English, 中文, 繁體中文, Русский, 日本語 ,한국어, Français, Español, عربي, Türkçe, Português (BR), فارسی, עברית, Italiano</div><hr />This is BETA. I'm going to work on LAB adjustments next.<h3 id="note:-you-need-to-update-comfyui-to-nightly-or-git-pull-comfyui-itself">Note: You need to update ComfyUi to Nightly or git pull ComfyUi itself</h3><h3 id="these-are-not-the-native-relay-vsr-nodes.-those-suck.-this-is-my-node.-do-not-get-confused.">These are NOT the native Relay VSR nodes. Those suck. This is my node. Do not get confused.</h3><hr />Read all about this <a target="_blank" rel="ugc" href="https://civarchive.com/articles/38504/rip-seedvr2-lc-relay-vsr-is-12x-to-22x-faster">HERE</a><hr /><h3 id="rip-seedvr2">RIP SeedVR2 🪦</h3><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/61115579-8d65-4689-9a26-911b1e6d305d/original=true/61115579-8d65-4689-9a26-911b1e6d305d.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c07fb3fc-1b02-4ebb-8015-bd50b4ee2c7f/original=true/c07fb3fc-1b02-4ebb-8015-bd50b4ee2c7f.jpeg" /><h2 id="lc-relay-vsr-upscale">LC Relay VSR Upscale 🧩</h2>What is it?<ul><li>Relay VSR in one node. The model, VAE and sampler are built in.</li><li>Use 2x or 4x for images 🖼️</li><li>2x or 4x for video 🎞️ (2x on smaller machines)</li><li>A fraction of the time VOSR2 or SEEDVR2 takes, and higher quality.</li><li>✋ The first run downloads the models: 5.2 GB per model, plus a 128 MB VAE, into <code>models/diffusion_models</code> and <code>models/vae</code>. A toast tells you it started. Press Stop to cancel. Already have them? They are found wherever they are.</li></ul>Settings ⚙️<ul><li>source:<ul><li>video: the frames are matched to each other, so the video stays steady. Use it for anything that came from a video.</li><li>image: every picture is upscaled on its own, so nothing carries over between them. Use it for a batch of different pictures. One picture comes out the same either way.</li></ul></li><li>upscale: 2x or 4x. Each one is its own model.</li><li>detail: 1.0 is the full model output. Lower moves toward a plain upscale.</li></ul>Video 🎞️<ul><li>Works on very low VRAM by scaling in batches. no need to combine at the endsource: video</li><li>upscale: 2x</li><li>✋ First run downloads the 2x model (5.2 GB).</li></ul><hr /><div data-type="blurb" data-id="230">Instagram: <a target="_blank" rel="ugc" href="https://www.instagram.com/synth.studio.models/">https://www.instagram.com/synth.studio.models/</a>Buy me a☕ <a target="_blank" rel="ugc" href="https://ko-fi.com/lonecatone">https://ko-fi.com/lonecatone</a>This represents many hours of work that I give away for free. If you enjoy it, Please make sure to 👍like and post to my workflows. That is how you support me. Also, feel free to ⚡tip 😉</div>

RIP SEEDVR2🪦. LC Relay VSR Upscale Model. (works for low VRAM) | Relay VSR 视频超分放大模型

RIP SEEDVR2 🪦 V2.0LC Relay VSR Upscale 🧩What is it?<ul><li>Relay VSR in one node. The model, VAE and sampler are built in.</li><li>Use 2x or 4x for images 🖼️</li><li>2x or 4x for video 🎞️ (2x on smaller machines)</li><li>A fraction of the time VOSR2 or SEEDVR2 takes, and higher quality.</li><li>✋ The first run downloads the models: 5.2 GB per model, plus a 128 MB VAE, into <code>models/diffusion_models</code> and <code>models/vae</code>. A toast tells you it started. Press Stop to cancel. Already have them? They are found wherever they are.</li></ul>Settings ⚙️<ul><li>source:<ul><li>video: the frames are matched to each other, so the video stays steady. Use it for anything that came from a video.</li><li>image: every picture is upscaled on its own, so nothing carries over between them. Use it for a batch of different pictures. One picture comes out the same either way.</li></ul></li><li>upscale: 2x or 4x. Each one is its own model.</li><li>detail: 1.0 is the full model output. Lower moves toward a plain upscale.</li></ul>Video 🎞️<ul><li>source: video</li><li>upscale: 2x</li><li>✋ First run downloads the 2x model (5.2 GB).</li></ul>

Files with SHA256: 4b653f782e5cf57f7dacd24b5dbadaa56253d8ec51ea09f9e6b4a232a94317d5