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/fixes:
The VAE input for "Checkpoint VAE" on the VAE Switch has been correctly connected to the Checkpoint Loader for the High model.
Cleaned up some of the Markdown Notes.
Added a Downscale group as a possible band-aid for jagged outputs when doing I2V.
If your image source is over-sharpened, this can possibly help. Your choice of upscale model used in this group matters. I use RealESRGAN_x4Plus Anime 6B for this.
FAQ
Comments (4)
Good overall workflow. Kudos. Is there a way to make this work with First/Last frame for the purpose of video looping? That really is the only thing this setup critically lacks.
Other people have asked before, but you can swap out the Wan Image to Video node for the First Last Frame version of it. It's one of the built in Comfy Core nodes.
I'm not going to guarantee the quality of the output though. My experience with FLF has been mixed and mostly bad.
darksidewalker's workflow has it as an option, if that's a must have feature for you and you don't want to add it yourself.
I just tested that node with the end_image input left empty and it effectively will work the same as the standard WanImagetoVideo node, so I will probably swap it out on the next update.
@Gladas Thank you very much for this update. Incidentally I've also had middling outputs at best. Looping is unfortunately a non negotiable for my use case.
Thanks again. Cheers.