Mindket

Kie.ai Veo video sub-workflow

Newversion 2 · updated

Overview

An n8n sub-workflow that another workflow calls to make one video on Kie.ai’s Veo model. It posts a prompt, a frame and reference images, checks the task every five seconds, and returns the first video address as resultUrls.

Kie.ai Veo video sub-workflow is an n8n workflow in the Developer category, listed by Mindket. It is free. This is version 2, last updated on . Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n.

At a glance

Runs in
  • n8n Cloud or your own server: import it next to the calling workflow
  • The calling workflow: an Execute Workflow node that picks this one and sends the four fields
  • AI product photo to video generator: it sends exactly these four fields to its sub-workflow
  • The node after the call: it receives resultUrls, ready to download or send on

Platform

Connects 1 app

How it works

Trigger

Called by another workflow

It starts when another workflow calls it through an Execute Workflow node, with four inputs:

  • video_prompt, the prompt
  • aspect_ratio, the frame
  • imageUrls, a list of image addresses
  • generationType

Actions

  1. Posts the four inputs to Kie.ai’s Veo generate endpoint, with the veo3_fast model
  2. Asks for the task’s status straight away
  3. While the task runs, waits five seconds and asks again
  4. On success, keeps the first video address and returns it

Result

The address of a finished video, returned to the calling workflow as resultUrls

Integrations

What you need before you start.

Kie.ai

Video generation

Makes the video from the prompt and images through its Veo generate endpoint, and reports the task’s status at record-info.

NeedsKie.ai API key

Workflow check

Checked by Mindket on 13 Nov 2026

Steps
7 steps, starting when another workflow calls it
AI
No step calls an AI model
Sign-ins
Signs in to: Kie.ai
API keys
No API key is left in the file; 1 blank in it for your own key
Step types
Mindket’s checker reads all 5 of its step types

Read from the workflow’s file, not from a run.

About

What it is

This n8n workflow is a building block. Another workflow calls it to make one video on Kie.ai’s Veo model, and it hands back the video’s address. Seven nodes do the work. It receives a prompt, a frame shape, a list of image addresses and a generation type, and posts them to Kie.ai. Then it asks for the task’s status, waits five seconds and asks again until the video is ready, and returns the first address as resultUrls. Those are the four fields Mindket’s AI product photo to video generator sends to its own video sub-workflow, so this file can fill that slot.

  1. Called with a prompt, a frame, images and a type
  2. Posts the request to Kie.ai’s Veo endpoint
  3. Asks for the task’s status
  4. While it runs, waits five seconds and asks again
  5. Returns the first video address as resultUrls

Who it suits

n8n builders who make video workflows and want the Kie.ai call, with its waiting loop, in one place that several workflows share. Skip it if you want something to press: it has no form or button of its own and runs only when another workflow calls it.

Who uses it, and how
IndustryWho uses itHow they use itExample
Online retailShop owners who automate their adsCall it from the photo-to-video workflow, once per productA shop’s workflow calls it for every new product photo.
AgenciesAutomation freelancersKeep the Kie.ai call in one place and reuse it across client workflowsA freelancer fixes an API change once, and three client workflows pick it up.
Social videoTeams that make Reels and ShortsSend 9:16 as the frame and get a vertical clipA team’s caller sets aspect_ratio to 9:16 for every run.
n8n developmentBuilders of long-running API callsCopy the submit, check and wait pattern for another serviceA builder reuses the loop for a different image API.

Where to use it

It runs on the same n8n as the workflow that calls it, because an Execute Workflow node can only pick a workflow from its own n8n.

  • n8n Cloud or your own server: import it next to the calling workflow
  • The calling workflow: an Execute Workflow node that picks this one and sends the four fields
  • AI product photo to video generator: it sends exactly these four fields to its sub-workflow
  • The node after the call: it receives resultUrls, ready to download or send on

Setup

Get it saves a zip with workflow.json and Mindket’s setup notes in your downloads folder. Its author puts setup at about 5 minutes.

What you need first
NeedDetail
n8nOn n8n Cloud or on a server of your own
Kie.aiAn account and its API key
A calling workflowOne with an Execute Workflow node, such as AI product photo to video generator
  1. In n8n, create a workflow, open its menu, choose Import from File and pick workflow.json.
  2. In Submit generation request and in Get request status, replace <YOUR_KIE_AI_API_KEY> in the Authorization header with your Kie.ai key. The brackets go too, so each header reads Bearer, a space and the key.
  3. Save the workflow. It does not need to be published, because another workflow starts it.
  4. In the calling workflow, open its Execute Workflow node, choose this workflow in the list and map the four fields.

How to use it

The caller sends four fields. Each goes to Kie.ai under the name the request needs.

The four fields
FieldTypeWhat to send
video_promptTextThe prompt for the video. It reaches Kie.ai as prompt
aspect_ratioTextThe frame, such as 16:9 or 9:16. It reaches Kie.ai as aspectRatio
imageUrlsList of addressesAddresses of the reference images, which Kie.ai must be able to open
generationTypeTextPassed on as it is. The photo-to-video listing sends REFERENCE_2_VIDEO

The file also fixes model at veo3_fast and sets enableFallback to true, both in the body of Submit generation request. Kie.ai’s own Veo pages explain what the fallback option changes.

Example

A caller sends this for a product shot.

{
  "video_prompt": "Cold brew bottle on a sunny café counter, slow dolly-in",
  "aspect_ratio": "9:16",
  "imageUrls": ["https://example.com/bottle.jpg"],
  "generationType": "REFERENCE_2_VIDEO"
}

The call comes back with one field, resultUrls, holding the first video address as text.

{ "resultUrls": "https://…" }

For newcomers and experts

If you are new. A sub-workflow is a workflow that other workflows call, the way a program calls a function. This one holds the slow part of making a video, which is sending the request and waiting for it. Test it from the calling workflow. Then open this one under Executions to see what each node received.

For experts. The status check runs once straight after the submit, with no wait, and later after each pause. Switch1 reads data.successFlag from Kie.ai’s reply.

What each status does
successFlagOutput of `Switch1`What happens
1CompletedEdit Fields keeps the first entry of data.response.resultUrls as resultUrls, and the call returns
0RetryWait2 pauses, Edit Fields14 copies data.taskId forward, and Get request status runs again
2FailedNo line leaves this output, so the run ends
3FailedThe same

Wait2 has no settings of its own, so it uses n8n’s default of five seconds for this version of the node. Change it there to poll less often.

Good to know

Each generation costs money, and a failed task ends without a message.

  • Billing: Kie.ai bills each generation to your account
  • Silent failure: flags 2 and 3 go nowhere, so the caller gets no item back and you read the run under Executions to see why
  • No retry limit: a task that stays at 0 is checked every five seconds until it changes
  • Your key: it sits in two header fields as plain text, so anyone who can open the workflow can read it. A header credential in n8n avoids that
  • Images: Kie.ai fetches them from the addresses you send, so private links will not work
  • Credentials: the JSON holds none, and nothing from its author’s account

README and files

README

Kie.ai Veo video sub-workflow

An n8n sub-workflow. Another workflow calls it with a prompt, a frame, a list of image addresses and a generation type, and
it returns the address of a video that Kie.ai's Veo model made.

It takes the four fields that Mindket's "AI product photo to video generator" listing sends to its own video
sub-workflow, so it can be the one that listing asks you to supply.

What is inside

  • workflow.json: the sub-workflow as n8n exports it, seven nodes. It holds no credential. Your Kie.ai key goes into
    two header fields.
  • README.md: these notes.

Before you start

  • An n8n instance, on n8n Cloud or your own server. The calling workflow has to be on the same one.
  • A Kie.ai account and its API key.
  • A calling workflow with an Execute Workflow node.

Set it up

  1. In n8n, create a workflow, open its menu and choose Import from File. Pick workflow.json.
  2. Open Submit generation request and Get request status. In each one's Authorization header, replace
    <YOUR_KIE_AI_API_KEY> with your Kie.ai key. The brackets go too, so the value reads Bearer, a space, then the key.
    If you prefer, delete those two headers and use an HTTP Header Auth credential with the same name and value.
  3. Save the workflow. It does not need to be published, because another workflow starts it.
  4. In the calling workflow, open its Execute Workflow node, choose this workflow in the list and map the fields below.

What it receives and returns

| Field | Type | What to send |
|---|---|---|
| video_prompt | text | The prompt for the video. It reaches Kie.ai as prompt. |
| aspect_ratio | text | The frame, such as 16:9 or 9:16. It reaches Kie.ai as aspectRatio. |
| imageUrls | list of addresses | Addresses of the reference images, which Kie.ai must be able to open. |
| generationType | text | Passed on as it is. The photo-to-video listing sends REFERENCE_2_VIDEO. |

It returns one item with one field, resultUrls: the first video address, as text.

How it runs

  1. Submit generation request posts the four fields to https://api.kie.ai/api/v1/veo/generate, with model fixed at
    veo3_fast and enableFallback set to true.
  2. Get request status asks https://api.kie.ai/api/v1/veo/record-info for the task, straight away.
  3. Switch1 reads data.successFlag. A 1 goes to Edit Fields, which keeps the first entry of
    data.response.resultUrls, and the call returns. A 0 goes through Wait2 and Edit Fields14 back to
    Get request status. A 2 or a 3 has no line out, so the run ends.

Wait2 has no settings of its own, so it waits n8n's default for this version of the node, five seconds. Change it there
to check less often.

Good to know

  • Kie.ai bills each generation to your account.
  • A failed task ends without a message and the caller gets no item back. Open the run under Executions to see the status.
  • Nothing limits the loop: a task that stays at 0 is checked until it changes.
  • Your key sits in two header fields as plain text, so anyone who can open the workflow can read it.
  • Kie.ai fetches the images from the addresses you send, so private links will not work.
  • Kie.ai's own Veo pages explain what enableFallback changes and what the other generation types need.
Files
README.md  3 KB
workflow.json  9 KB

2 files, 12 KB, downloaded as a zip.

What’s new

  • Version 2 · 2026-11-09

    Updated by Mindket to the current version of this kit.

  • Version 1 · 2026-11-03

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

Bonsai-27B-GGUF

lmstudio-community · Kit

A GGUF conversion of the 27B Bonsai model for LM Studio, with a 3.80 GB Q1_0 language file and a 0.93 GB BF16 vision projector. Tested for text, vision and par…

New

Runs DeepSeek-V4.1-Flash-1017 as a 2.9 bits-per-weight EXL3 quantization, a 196 GiB copy for people serving large models on their own hardware. Perplexity stay…

New

MusicGen Small

facebook · Kit

Generates short music clips from a text description or an audio prompt, in the small checkpoint of facebook's MusicGen. It suits developers and music hobbyists…

New

Similar in Developer

See all in Developer

Lexnet

alpindale · Kit

Tags every character of C source code for syntax highlighting with a tiny neural network of about 984 weights, run through a small C program. For developers an…

New

FLUX.2 Klein LoRA Studio

prithivMLmods · Kit

Try a set of LoRAs for the FLUX.2 Klein image model in a Gradio app that runs in your browser or on your own computer. Made for people who make or test AI imag…

New

anaksor-ocr

Sokheng · Kit

Reads Khmer and English text from documents, receipts and photos of signs, using a detector for text lines and a recogniser for each line. Suits developers who…

New