<h2 id="workflow-overview:-lightspeed-wan-series">Workflow Overview: Lightspeed Wan Series</h2>These workflows are optimized for the Lightspeed Wan 2.1 and 2.2 Image-to-Video (I2V) models by darksidewalker. They are categorized into the streamlined SVI-V2-Pro series and the feature-rich Standard (v12 and below) series.<hr /><h2 id="1.-svi-v2-pro-i2v-(barebone-series)">1. SVI-V2-Pro-I2V (Barebone Series)</h2>The SVI series is designed for users who want a clean workspace without unnecessary overhead. It focuses on the core I2V logic with two critical utility modules.<h3 id="a.-resolution-management-(resolution-master)">A. Resolution Management (Resolution Master)</h3>To ensure compatibility with Wan 2.2’s specific latent requirements, the source image must be precisely resized.<ul><li>Step 1: Load the source image into the Load Image node.</li><li>Step 2: Use the dropdown (next to the TV icon) to select a target resolution (e.g., 480p, 720p).</li><li>Step 3: Click the TV Icon to activate the selection.</li><li>Step 4: Under 'Actions', set the slider to 16 and click the Snap button.<ul><li>Note: This "snapping" ensures the dimensions are multiples of 16, preventing tiling artifacts or model errors.</li></ul></li></ul><h3 id="b.-temporal-smoothing-(interpolation)">B. Temporal Smoothing (Interpolation)</h3>Located in a dedicated group, this module handles frame rate conversion.<ul><li>Primary Use: Converting low-FPS raw generations (e.g., 16 FPS) into smooth, high-fidelity output (e.g., 60 FPS).</li></ul><hr /><h2 id="2.-standard-wan-workflows-(v12-and-below)">2. Standard Wan Workflows (v12 and Below)</h2>The legacy/standard workflows are "all-in-one" solutions, containing a broader suite of post-processing and utility tools:Image to Video<ul><li>The core generative engine for Wan 2.1/2.2.</li></ul>FLF Loop<ul><li>Facilitates seamless looping by utilizing First-Last Frame logic.</li></ul>Downscale Image<ul><li>Safely shrinks oversized source images to prevent VRAM OOM (Out of Memory) errors.</li></ul>Extract Last Frame<ul><li>Pulls the final frame of a generation to be used as a starting point for the next clip (Storyboarding).</li></ul>Combine Videos<ul><li>Merges multiple generated clips into a single sequence.</li></ul>Interpolation<ul><li>Increases frame rate for smoother motion.</li></ul>Upscale Video<ul><li>Increases the spatial resolution of the final video output.</li></ul>

Not so Simple (or is it?) Wan 2.1/2.2 Lightspeed I2V Workflow

Rearranged some of the nodes to make it easier(-ish) in case anyone disconnects something by accident.Added manual switches for CLIP and VAE models.<ul><li>Now you can toggle between 1 (Checkpoint) or 2 (Loader).</li></ul>Removed the 2 KSamplers and replaced them with a single <a target="_blank" rel="ugc" href="https://github.com/stduhpf/ComfyUI-WanMoeKSampler">WanMoeKSampler</a><ul><li>This is connected to <a target="_blank" rel="ugc" href="https://github.com/cmeka/ComfyUI-WanMoEScheduler">WanMoEScheduler</a></li><li>Sampler and Scheduler will have to be set on these nodes.</li><li>You probably should use the same scheduler setting on both, but you do you.</li><li>Check their project pages if you want explanations on how they work.</li><li>I'm just throwing spaghetti at the wall with these based on the info on their project pages.</li></ul>I don't claim to be an expert on Wan or how it works. You're all either learning with me or just enjoying the success and failures of my experimenting!Tested on the High+Low versions of this <a target="_blank" rel="ugc" href="https://civitai.com/models/1981116?modelVersionId=2342708">model</a>.<ul><li>A 480p 5-second video takes 2 minutes on my 5060ti 16GB + 64GB RAM (using the recommended 4 steps). This is plenty fast enough for me considering my hardware.</li></ul>

Files with SHA256: cc8222d820ab74ebcfc44babbff53a8d6af32b141db92c83d564d1b9942e9d64