WorkflowListedExternal

WAN 2.2 I2V - Simple multiple prompt/video loop — v1.0

A very simple WAN 2.2 workflow, aimed to make as simple as the native one while being able to create any number between 1 and 10 videos to be stitched together.

Sourcecivitai.com/models/1836348

TaskImage to imageFamilyWanEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access: External workflow
Status: Listed
Source: Civitai
Updated: Oct 2, 2026

Source description

A very simple WAN 2.2 workflow, aimed to make as simple as the native one while being able to create any number between 1 and 10 videos to be stitched together.

Uses the usual attempt of previous video's last frame to next video's first frame.

You manually only need to input it like the native workflow (as in: load models - optionally with LoRAs -, load first frame image, set image size and length).

The main difference is the prompting: Input multiple prompts separated by "|" to generate multiple videos using the last frame.

Since there's no VACE model of 2.2 available currently you can expect a loss of motion in between, but generally speaking even 30-50 second videos turn out better than with WAN 2.1 according to my (limited) tests.

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

Use WAN 2.2 I2V - Simple multiple prompt/video loop to create 1–10 stitched videos from models, optional LoRAs, a first-frame image, image size, video length, and prompts separated by “|”; each video passes its last frame to the next.

Flow

Load the models, optionally load LoRAs, add the first-frame image, and set the image size and video length.
Separate prompts with “|” to generate multiple videos using the previous video’s last frame, then stitch the videos together.

Inputs and outputs

Inputs are models, optional LoRAs, a first-frame image, image size, video length, and prompts separated by “|”.
The output is 1–10 stitched videos, with each later video using the previous video’s last frame as its first-frame input.

Setup

The listed base model is Wan Video 14B i2v 720p, and the publisher is Yorgash.
No license is listed.

Dependencies

The listed node packs are: comfyui_essentials, comfyui_llm_party, comfyui_tinyterranodes, ComfyUI-Crystools, comfyui-easy-use, comfyui-kjnodes, ComfyUI-QualityOfLifeSuit_Omar92, and mikey_nodes.
Before using it, verify that your setup has these model files: CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors, and wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors.
Suggestion
The listed LoRA files are: Wan21_AccVid_I2V_480P_14B_lora_rank32_fp16.safetensors and Wan21_I2V_14B_lightx2v_cfg_step_distill_lora_rank64_fixed.safetensors.

Configuration

Use “|” between prompts to generate multiple videos connected through the previous video’s last frame.

Cautions

Motion may be lost between clips because no VACE model of 2.2 is currently available.

Does this need to be edited?

Sources

1 source

CivitaiPrimary

civitai.com/models/1836348

Verified Jul 19

Source excerpts

1 excerpt

NoteJul 19civitai.com/models/1836348

Source context: 3265 downloads · Type Workflows · Base model Wan Video 14B i2v 720p