Wan2.2 Remix I2V — Long Video (~30s) Workflow
Image-to-Video workflow for generating ~30-second videos using Wan2.2 Remix v3.0 with a two-pass (Low→High) sampling approach.
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
| Type | File |
|---|---|
| UNET (Low) | wan22RemixT2VI2V_i2vLowV30.safetensors |
| UNET (High) | wan22RemixT2VI2V_i2vHighV30.safetensors |
| CLIP | nsfw_wan_umt5-xxl_fp8_scaled.safetensors |
| VAE | Wan2_1_VAE_bf16.safetensors |
Required Custom Nodes
- ComfyUI-VideoHelperSuite —
VHS_VideoCombine - ComfyUI-PainterVRAM — VRAM management
- rgthree-comfy —
Seed
Usage
- Load an image into the
LoadImagenode - Edit the positive prompt for each segment to describe scene progression
- 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.
- Downloads last month
- -