Wan2.2 Remix I2V — Long Video (~30s) Workflow

Overview

• 7 segments × 81 frames each, chained sequentially (last frame → next segment's input)
• Two-pass KSampler: Low model (steps 0–10) → High model (steps 10–12)
• Output: 720×1280, 16fps, H.264 MP4

Required Models

Required Custom Nodes

• ComfyUI-VideoHelperSuite — VHS_VideoCombine
• ComfyUI-PainterVRAM — VRAM management
• rgthree-comfy — Seed

Usage

1. Load an image into the LoadImage node
2. Edit the positive prompt for each segment to describe scene progression
3. Queue and wait — each segment generates sequentially

Each segment's prompt is independent, so you can tell a story that evolves across the 7 segments.