Workflow Overview: Lightspeed Wan Series
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.
1. SVI-V2-Pro-I2V (Barebone Series)
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.
A. Resolution Management (Resolution Master)
To ensure compatibility with Wan 2.2’s specific latent requirements, the source image must be precisely resized.
Step 1: Load the source image into the Load Image node.
Step 2: Use the dropdown (next to the TV icon) to select a target resolution (e.g., 480p, 720p).
Step 3: Click the TV Icon to activate the selection.
Step 4: Under 'Actions', set the slider to 16 and click the Snap button.
Note: This "snapping" ensures the dimensions are multiples of 16, preventing tiling artifacts or model errors.
B. Temporal Smoothing (Interpolation)
Located in a dedicated group, this module handles frame rate conversion.
Primary Use: Converting low-FPS raw generations (e.g., 16 FPS) into smooth, high-fidelity output (e.g., 60 FPS).
2. Standard Wan Workflows (v12 and Below)
The legacy/standard workflows are "all-in-one" solutions, containing a broader suite of post-processing and utility tools:
Image to Video
The core generative engine for Wan 2.1/2.2.
FLF Loop
Facilitates seamless looping by utilizing First-Last Frame logic.
Downscale Image
Safely shrinks oversized source images to prevent VRAM OOM (Out of Memory) errors.
Extract Last Frame
Pulls the final frame of a generation to be used as a starting point for the next clip (Storyboarding).
Combine Videos
Merges multiple generated clips into a single sequence.
Interpolation
Increases frame rate for smoother motion.
Upscale Video
Increases the spatial resolution of the final video output.
Description
Minor changes:
Added a note for some suggested settings for Image Filter Adjustments.
The upscale with model nodes are now in a group that can be toggled off.
Replaced the Load Video nodes with the ffmpeg versions.
Added Color Match nodes to help keep the color consistent when going through the process of making multiple videos to combine into a single video.
FAQ
Comments (5)
First of many WAN Workflows that worked out of the box for me. Good job
Thanks! I'm new to using WAN, so I am glad it is helping others as well.
@Gladas some things i noticed.
- The first image upscale is not really necessary if you already start out with a sufficient sized image
- It would make more sense to throw in an upscale with model (x2 should be enough) before or after the rife frame interpolator to upscale the final video
- can you do a key frame generation too? like input 2 images one for the start and one for the end, and keep the prompt for how it goes from 1->2?
@Nemu86 the 1st upscale is more of a downscale function for me. I use it when taking a large image and downscale it with the help of the upscale model. It removes all the jagged edges (at least for me). Most of my earlier videos had some serious jagged edges and this was what fixed it.
The RealESRGAN model I use does the job nicely, but people can use (or not use) whatever they want.
As far as upscaling after: my PC wants to die when trying that, so that's a pass for me. I think anyone can add it themselves if they really want it.
The key frame generation thing is not something I know anything about. I am new when it comes to video generation. Sounds interesting though.
This workflow is just what I use personally. I would like to keep it fairly simple, since it already bogs down my PC as-is.
Works flawlessly! Thanks.