Photo motion transfer from a video clip

What it is

This n8n workflow makes a still portrait move the way a video clip moves. A form takes the portrait and a source clip, and RunningHub stores both. Then a RunningHub AI app transfers the clip’s motion onto the image. n8n waits five minutes, checks the task, and keeps checking once a minute until the task succeeds or fails. Fifteen nodes run in two stretches: the first uploads the files and starts the task, and the second waits, fetches the result and downloads each video file it lists.

Who it suits

Creators and small teams who want a character, a portrait or a piece of concept art to perform a movement they can film or find. Skip it if you want to steer the result with words from inside n8n. The app has a prompt field. The file leaves it empty.

Where to use it

Any n8n that can reach runninghub.ai will run it. The form is the front door, so you share its address with whoever supplies the files.

• n8n Cloud: import the file into a new workflow there
• Your own n8n server: the same file and steps
• The form’s address: send it to the people who provide the portraits and clips
• Anything after `downloadVideo`: add a node there to save each video or send it 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 14.5 minutes.

1. In n8n, create a workflow, open its menu, choose Import from File and pick workflow.json.
2. Open API Setup and replace YOUR_RUNNINGHUB_API with your RunningHub API key.
3. If you want, open On form submission and change the form’s title or the file types it accepts.
4. To steer the motion with a prompt, open createTask and type one into fieldValue of the entry whose nodeId is 164. The file leaves it empty.
5. Save, open the form’s test address and send a portrait and a clip through it.
6. Press Publish, then share the form’s production address.

How to use it

Open the form, attach a portrait and a video clip, and send them. Both fields are required. Each takes one file. The image can be .jpg, .jpeg, .png or .webp, and the clip .mp4, .avi, .mov or .mkv. The form confirms at once. The run goes on behind it. The video lands in the run’s execution data, so open the run under Executions to get it.

Example

A designer uploads a .png of a cartoon fox and a short .mp4 of someone turning their head and smiling. Five minutes after the task starts, the first status check runs, and once a minute after that until the status reads SUCCESS. Then downloadVideo holds a video of the fox turning its head and smiling.

For newcomers and experts

If you are new. n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. Here the heavy work happens on RunningHub, and n8n only carries files to it and waits. The key you paste into API Setup is how RunningHub knows the calls are yours. Send a test through the form first, since each node then shows what it received and sent.

For experts. The file talks to RunningHub in two styles. Upload and output calls carry your key as apiKey in the body. The task and status calls send it as a Bearer header, on a newer path.

The two uploads run side by side, and Merge and Aggregate fold their replies into one item. createTask then puts the image’s name in node 163 of the app and the video’s in node 178. After a SUCCESS, Code in JavaScript turns each entry of data into its own item, so downloadVideo fetches every file the app returns.

Good to know

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

• Billing: RunningHub bills each task to your account, and the file asks for the plus instance type, so check what that costs there
• No failure path: output 0 of Switch, for FAILED, goes nowhere, so open the run under Executions when no video appears
• Late first check: the first status check comes five minutes after the task starts, so a quick failure shows up late
• No retry limit: a task that stays queued or running is checked every minute until it finishes
• Open form: once the workflow is published, anyone with the form’s address can start a run on your RunningHub account
• Your key: it sits as plain text in API Setup, so anyone who can open the workflow can read it
• Your files: the portrait and the clip are uploaded to RunningHub, and the people in them should be ones you have the right to use
• Credentials: the JSON holds none, and nothing from its author’s account