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
Release Notes: Wan 2.2 I2V (SVI V2 Pro) Update v2
This update focuses on improving generation stability and streamlining the control flow of the workflow. While it remains a "no-frills" setup dedicated to Image-to-Video and interpolation, these changes offer more granular control over the diffusion process.
On my 5060ti: generating 480p video with all Sampler Groups enabled and length for each set to 81 takes 16 to 17 minutes.
What’s New
Individual RandomNoise Nodes: Each of the 6 Sampler Groups now features its own RandomNoise node. This provides better entropy management across the multi-stage generation.
Normalized Attention Guidance (NAG): I have integrated NAG nodes into every Sampler Group.
Function: This applies the negative prompt at CFG 1, which can help maintain composition integrity without the "burnt" look sometimes associated with high CFG scales.
Decoupled Positive Prompts: The "Lazy Positive Prompt" primitive node has been removed.
Reason: Testing suggests that SVI performs more reliably when positive CLIP Text Encode nodes are handled individually within their respective groups.
Fast Groups Bypasser Logic: For easier workflow management, Fast Groups Bypasser nodes have been added at both the beginning and the end of the graph. This allows you to quickly toggle entire sections of the logic without manual mucking.
Core Functionality
I2V + Interpolation: This remains a specialized, transparent tool for image-to-video generation and subsequent interpolation.
Manual Control: Designed for those who prefer to see exactly how the logic is constructed and avoid "black box" node setups.
Disclaimer
This workflow was built to satisfy a specific request and represents my early explorations with SVI. If you are looking for a highly polished, feature-heavy "bells and whistles" experience, you may want to consult more established SVI workflows in the community.