V11 - Updated for compatibility with recent ComfyUI versions (ComfyUI Frontend versions &gt; 1.40.0.x totally borked subgraphs).V10 - Use with ComfyUI Frontend versions &lt;= 1.40.0.x<h2 id="this-is-my-take-on-an-&quot;ultimate-wan-2.2-i2v-svi&quot;-workflow.">This is my take on an "ultimate WAN 2.2 I2V / SVI" workflow.</h2><h3 id="i-can-only-recommend-using-this-wf-if-you-are-also-using-comfyui-easy-install.-it-seems-that-the-some-of-the-very-popular-&quot;must-have&quot;-nodes-i've-used-which-are-included-in-this-may-be-problematic-for-users-who-are-not-using-it.">I can only recommend using this WF if you are also using <a target="_blank" rel="ugc" href="https://github.com/Tavris1/ComfyUI-Easy-Install">ComfyUI-Easy-Install. </a>It seems that the some of the very popular "must-have" nodes I've used, which are included in this, may be problematic for users who are NOT using it.</h3>Convenience features:- Global LoRAs option. Each gen step can have additional LoRAs.- Global prompt prefix/suffix option. Each gen step can have this customized.- Each gen step has option to "Save latent" (can be loaded later for SVI extension)- Color correction option for each gen stepCan independently run I2V or SVI or both- Starting point for I2V can be First Frame ***or*** FLF2V (first/last) ***or*** FMLF2V (first/middle/last)- Start point for SVI can be I2V ***or*** load a saved latent ***or*** load a video fileSVI blocks:- Can have overrides for Shift, Total Steps, Split Step- Can be duplicatedMy custom Image Resize node can be found here:<a target="_blank" rel="ugc" href="https://github.com/altoiddealer/comfyui_essential-er">https://github.com/altoiddealer/comfyui_essential-er</a>The "Save/Load" Latents node can be found here:<a target="_blank" rel="ugc" href="https://github.com/A1-multiply/ComfyUI-LatentSaver">https://github.com/A1-multiply/ComfyUI-LatentSaver</a>I also used a few nodes that I like from this node pack:<a target="_blank" rel="ugc" href="https://github.com/jamesWalker55/comfyui-various">https://github.com/jamesWalker55/comfyui-various</a>Recommended models:SmoothMix V2 - High NoiseDaSiWa Lightspeed SynthSeduction v9 - Low NoiseRecommended parameters:Shift: 5.0High noise steps: 3Low noise steps: 4cfg: 1.0Sampler: lcmScheduler: beta

WAN 2.2 Image to Video (I2V) 14B with SVI 2.0

Updated for compatibility with ComfyUI Frontend &gt; 1.40.0.x

Files with SHA256: 9e9b3131cdceb73571f355944d95b7f156d06f23627f6561a18de8357a8888b8