Skip to content
WorkflowListedExternal
Download

Wan2.2 Highspeed "FreeLength(Loop Processing)" I2V Workflow for Your Scenario (Start/End FLF2V) — v1.0

This is an I2V workflow created for Wan2.2.

TaskImage to imageFamilyWanVersionRelease 2104690 — Wan2.2-Highspeed_FreeLength_FLF2V-I2V_WithScenario_20250811v2.jsonEstimated VRAMNot yet characterizedUnratedgrade

Runtime profile

Access
External workflow
Status
Listed
Version
Wan2.2-Highspeed_FreeLength_FLF2V-I2V_WithScenario_20250811v2.json
Source
Civitai
Updated
Nov 3, 2026

Source description

No release description captured.

What you need

Model files
23.5 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Requirements

Models

10

Node packs

18
  • cg-image-filter

    Found

    Node pack · Registry

  • comfyliterals

    Found

    Node pack · Registry

  • ComfyUI_Comfyroll_CustomNodes

    Found

    Node pack · Registry

  • comfyui_essentials

    Found

    Node pack · Registry

  • ComfyUI_Ib_CustomNodes

    Found

    Node pack · Registry

  • comfyui_layerstyle

    Found

    Node pack · Registry

  • comfyui-custom-scripts

    Found

    Node pack · Registry

  • Node pack · Registry

  • comfyui-frame-interpolation

    Found

    Node pack · Registry

  • comfyui-gguf

    Possible

    Node pack · Registry

  • comfyui-kjnodes

    Found

    Node pack · Registry

  • comfyui-ollama

    FoundOptional

    Node pack · Registry

  • comfyui-videohelpersuite

    Found

    Node pack · Registry

  • Fast Groups Muter (rgthree)

    Not resolved

    Node pack · Unknown

  • GetNode

    Not resolved

    Node pack · Unknown

  • rgthree-comfy

    Found

    Node pack · Registry

  • SetNode

    Not resolved

    Node pack · Unknown

  • was-ns

    Not resolved

    Node pack · Registry

AI-generated commentary

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

Purpose

  • This Wan2.2 image-to-video workflow uses a start image, an end image, and scene prompts to join loop outputs into a video; its description says it can make videos of any length.

Flow

  • Each prompt line describes one scene, and the number of lines sets the number of loop iterations.

Inputs and outputs

  • Prepare the final-frame image in advance and put its path in the fourth prompt field: duration (seconds) | character action | camera work | end_image filepath.

  • Choose this version when you can provide both a start image and an end image; a similar start-image-only version is listed separately.

    Suggestion

Setup

  • Version v1.0 is listed for Wan Video 2.2 I2V-A14B.

Dependencies

  • The workflow lists these add-ons: cg-image-filter, comfyliterals, ComfyUI_Comfyroll_CustomNodes, comfyui_essentials, ComfyUI_Ib_CustomNodes, comfyui_layerstyle, comfyui-custom-scripts, comfyui-easy-use, and comfyui-frame-interpolation.

  • It also lists comfyui-gguf, comfyui-kjnodes, comfyui-ollama, comfyui-videohelpersuite, Fast Groups Muter (rgthree), GetNode, rgthree-comfy, SetNode, and was-ns.

  • The model-file list names clip_vision_h_fp8_e4m3fn.safetensors, DetailEnhancerV1.safetensors, lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors, rife49.pth, umt5_xxl_fp8_e4m3fn_scaled.safetensors, usako_comfyui.safetensors, wan_2.1_vae_fp32.safetensors, Wan2.1_T2V_14

Configuration

  • To set Length for each loop, use (Duration [seconds] × FPS) ÷ (Frame interpolation count + 1) + 1; the value can vary by loop.

    Suggestion · not verified

  • If reference-image color shifts occur after many loops, try adjusting Image Desaturate.

    Suggestion · not verified

Cautions

  • KSampler input and output frame counts may differ; the description warns that a mismatch may degrade the output image.

  • Before setup, confirm which packages provide Fast Groups Muter (rgthree), GetNode, and SetNode.

    Suggestion

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimaryVersion 2104690
civitai.com/models/1859632

Verified Nov 3

Workflow instructions

Author notes from Wan2.2-Highspeed_FreeLength_FLF2V-I2V_WithScenario_20250811v2.json · selected release

You are the top art director; I need some inspiration to create stunning images using Wan2.1. I need the text prompt from your inspiration idea with the following structure: subject, scene, and action. All 3 element write in one paragraph with natural English sentences format. Here is the instruction: The subject includes humans, animals, or any imagined subject The scene includes the environment in which the subject is located, including the foreground, and can be a real scene or an imagined fictional scene Actions include the movement state of the subject or non subject, which can be small, large, delicate, or partial movements, or overall movements.

Author notes from Wan2.2-Highspeed_FreeLength_FLF2V-I2V_WithScenario_20250811v2.json · selected release

Always effective. Applies within all loops. Describe the characteristics of the main character.

Author notes from Wan2.2-Highspeed_FreeLength_FLF2V-I2V_WithScenario_20250811v2.json · selected release

Valid within individual loops (line-by-line). *** The format MUST BE as follows. *** Syntax: duration(second)|character's action|camera work|end image's file path (Split with "|") Example: 3|She is drinking water.|The camera is closing to her.|D:\AI\Scenario-002.png 2|She turned around and smiled.|The camera focuses on her face.|D:\AI\Scenario-003.png

Download files

Model artifacts

2 artifacts

wan22HighspeedFreelengthLoop_v10.zip

zip · 19.2 KB · SHA-256 65278634b8cc…92ae · Civitai

Download file

Wan2.2-Highspeed_FreeLength_FLF2V-I2V_WithScenario_20250811v2.json

json · 160 KB · SHA-256 2e6c6bd17a4a…5b7a

Download file

Source excerpts

3 excerpts

Source context: 450 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B

Source context: 428 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B

Source context: 392 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B