WAN 2.2 Smooth Workflow v5.0 in ComfyUI | Multi-Mode Video Gen

Turn text or images into silky-smooth short videos instantly.

Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not for: one-click results with zero tuning - you still choose inputs, prompts, and settings.

Open preloaded workflow on RunComfy

Open preloaded workflow on RunComfy (browser)

Why RunComfy first
- Fewer missing-node surprises - run the graph in a managed environment before you mirror it locally.
- Quick GPU tryout - useful if your local VRAM or install time is the bottleneck.
- Matches the published JSON - the zip follows the same runnable workflow you can open on RunComfy.

When downloading for local ComfyUI makes sense - you want full control over models on disk, batch scripting, or offline runs.

How to use (local ComfyUI)
1. Load inputs (images/video/audio) in the marked loader nodes.
2. Set prompts, resolution, and seeds; start with a short test run.
3. Export from the Save / Write nodes shown in the graph.

Expectations - First run may pull large weights; cloud runs may require a free RunComfy account.

Overview

This ComfyUI-ready pipeline built on SmoothMix WAN 2.2 models lets you create cinematic short clips from text, images, or audio inputs. With Lightx2v LoRAs and RIFE interpolation, it produces ultra-smooth five-second videos. You can animate between first and last frames and seamlessly switch between T2V, I2V, F2LF, and A2V tasks. Designed for creators who demand flexibility and polished outcomes, it simplifies complex video generation into an organized, ready-to-run canvas.

Important nodes:

Key nodes in Comfyui WAN 2.2 Smooth Workflow v5.0

WanImageToVideo (#50)
- This is the WAN 2.x video entry point for both T2V and I2V inside WanVideoWrapper. It merges your prompts with the VAE (and an optional start image) to build an initial motion latent. Size and length controls upstream must respect model‑friendly constraints, and this node feeds the paired samplers that follow. WanVideoWrapper implementation details and updates are maintained here: kijai/ComfyUI-WanVideoWrapper.

WanFirstLastFrameToVideo (#343)
- Drives the First‑to‑Last‑Frame path by ingesting CLIP Vision embeddings for both boundary frames together with your text prompts. It creates a guided trajectory that preserves subject identity and scene layout while morphing toward the target. Keep start and end frames aligned in subject scale and composition for the most natural transitions.

KSamplerWithNAG (Advanced) (#234)
- Applies Noise Assisted Guidance to improve prompt adherence and reduce temporal drift in short clips. Adjust its guidance only when you see over‑constraint or under‑constraint; it works in tandem with the standard sampler and your negative prompt. See the method and tuning guidance in the project docs: scottmudge/ComfyUI-NAG.

RIFEInterpolation (#160)
- Inserts high‑quality in‑betweens to improve motion smoothness before encoding to video. Use it when your base sequence looks good frame‑to‑frame but feels a little choppy at playback. The node integrates the RIFE implementation provided by the ComfyUI VFI extension. GACLove/ComfyUI-VFI

VHS_VideoCombine (#77)
- Handles final encoding, muxing optional audio, and saving metadata. Keep its format and pixel format consistent across projects for predictable playback. VideoHelperSuite also powers the quick last‑frame preview utilities used elsewhere on the canvas. pythongosssss/ComfyUI-VideoHelperSuite

Notes

WAN 2.2 Smooth Workflow v5.0 in ComfyUI | Multi-Mode Video Gen - see RunComfy page for the latest node requirements.