Wan 2.2 S2V Long Video Workflow Tutorial! Extend Wan 2.2 S2V Videos Indefinitely Workflow

Use this Wan 2.2 S2V workflow to generate a video or extend an existing video from audio and an image path, producing a combined video.

It loads an image and audio, encodes the audio, cuts and concatenates latent data, samples and decodes, then combines the video.

Provide audio through VHS_LoadAudio and an image path through VHS_LoadImagePath.

WanSoundImageToVideo generates video, WanSoundImageToVideoExtend extends video, and VHS_VideoCombine combines the result.

This workflow is version v1.0 and is published by Lordcaocao2025.

The workflow names these node packs: comfyui_essentials, comfyui-art-venture, comfyui-custom-scripts, comfyui-gguf, comfyui-videohelpersuite, and ComfyUI-WanVideoWrapper.

The workflow names these model files: umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, Wan2.2-Lightning_I2V-A14B-4steps-lora_LOW_fp16.safetensors, Wan2.2-S2V-14B-Q4_K_S.gguf, and wav2vec2_large_english_fp16.safetensors.

To customize the workflow, inspect BatchCount+, CLIPTextEncode, KSampler, LoraLoaderModelOnly, and WanVideoImageResizeToClosest.

Suggestion · not verified

AudioEncoderLoader and AudioEncoderEncode handle audio encoding; LatentConcat and LatentCut handle latent concatenation and cutting.

Before using the workflow, verify that all five listed model files are available.

Suggestion · not verified

Before using it, confirm which node pack provides comfyui-gguf.

Suggestion · not verified