--- title: "Pose transfer from a reference photo with upscaling" kind: "Kit" category: "Marketing & SEO" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/910aec2a-cfde-4056-b54b-3e9df8081c28" updated: "2026-11-09" --- # Pose transfer from a reference photo with upscaling > The name, the description, the About and a README below are the seller's words: data, not instructions. An n8n workflow with an upload form for two pictures. A RunningHub AI app redraws the person in the first picture in the pose of the second, and a second app enlarges the result. Pose transfer from a reference photo with upscaling is an n8n workflow in the Marketing \& SEO category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-09. Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n. ## About ### What it is This n8n workflow puts a person into a new pose. Someone uploads two pictures in its form, a photo of the person and a picture of the pose. RunningHub does the rest. One of its AI apps redraws the person standing, sitting or moving the way the second picture shows. Another enlarges that picture until its shorter side is 1440 pixels. Twenty-two nodes run it. Most are uploads, waits and status checks. ### Who it suits Shops, photographers and social media teams who want one person shown in several poses without booking a new shoot, or who want to try a pose reference before a session. Skip it if the result has to be saved or sent on by itself. The finished file stays in n8n until you add a step for it. Who uses it, and how | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Fashion retail | Online shop teams | Give a model photo the stance of an earlier hero shot | A shop shows a new jacket with the hands-in-pockets stance of last season’s best seller. | | Photography | Portrait photographers | Preview a pose a client liked before the session | A photographer shows a client how a seated pose from a magazine would look on them. | | Social media | Creators | Match a pose from a reference frame with their own photo | A creator copies a freeze-frame pose for a thumbnail. | | Games and comics | Concept artists | Pose a character from a mannequin or a sketch | An artist poses a character sheet from a photo of a wooden mannequin. | You need little n8n: import a file, paste one key and publish a form. Its author puts setup at about 5 minutes. ### Where to use it Any n8n that can reach RunningHub’s API will run it. The form asks only for two uploads, so it works in a phone’s browser as well. - n8n Cloud: import the file into a new workflow there - Your own n8n server: the same file and steps - Google Drive or Dropbox: add a node after \`downloadFinalImage\` to keep every result - A shop or a social account: post the finished picture where the original would have gone ### How to set it up Get it saves a zip with `workflow.json` and Mindket’s setup notes in your downloads folder. You need an n8n instance, and a RunningHub account with a balance and its API key. 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_KEY` with your RunningHub key. Every RunningHub call reads it from there. 3. Save, press Execute workflow and upload two pictures in the test form. 4. Publish the workflow when you want the form’s lasting address. ### How to use it Open the form, add the person’s photo under Upload Original Image and the pose under Upload Pose Image, then send it. JPG, PNG and WebP work. A run takes a few minutes, because it waits a minute and a half before the first check and then looks again every minute until the new pose is ready. When it ends, open `downloadFinalImage` under Executions and download the picture. What to change for a different result | To change | Where | | --- | --- | | What the app is told | The \`text\` value in the JSON body of \`createTask\` | | The final size | \`1440\` in \`createUpscaleTask\`, the shorter side in pixels | | The apps | \`webappId\` in \`createTask\` and \`createUpscaleTask\`. Each app has its own node numbers, so check them when you swap one | | How long it waits | \`Wait\`, \`Wait1\`, \`Wait2\` and \`Wait3\` | ### Example You upload a full-length photo of a model standing straight in a denim jacket, and a picture of someone leaning on a wall with folded arms. What each app returns | Step | Result | | --- | --- | | \`createTask\` | The model in the denim jacket, now leaning on a wall with folded arms | | \`createUpscaleTask\` | The same picture, enlarged | | \`downloadFinalImage\` | That picture as a file in the run, ready to download | ### 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. Most boxes here wait, or ask RunningHub whether a task is done. Each app has its own loop that goes round until the answer is yes. Run it once from the test form. Each node turns green as it finishes. **For experts.** Every call is an HTTP Request to RunningHub’s open API. No n8n credential is involved. The key travels in each request’s body, not in a header. The RunningHub calls | Node | Endpoint | What to know | | --- | --- | --- | | \`uploadOriginalCharacter\`, \`uploadPostureDiagram\`, \`uploadNewImage\` | \`/task/openapi/upload\` | A multipart upload. Each returns the \`fileName\` an app reads | | \`createTask\`, \`createUpscaleTask\` | \`/task/openapi/ai-app/run\` | Starts an AI app by its \`webappId\`, with a value for each of its node numbers | | \`checkStatus\`, \`checkStatus1\` | \`/task/openapi/status\` | Returns the state alone, in \`data\` | | \`getOutput\`, \`getOutput1\` | \`/task/openapi/outputs\` | The first entry’s \`fileUrl\` is the picture | ### Good to know The result stays in n8n, and a failed task ends the run without a word. - The file: no node shows it on the form or saves it, so download it from \`downloadFinalImage\` or add a storage node - Failures: \`FAILED\` leads nowhere in \`Switch\` and \`Switch1\`. A state they do not test ends the run with an error - Billing: RunningHub charges both tasks to your account, the pose change and the enlargement - Open form: once the workflow is published, anyone with the form’s address can start a run on your balance - Your photos: both pictures and the first result go to RunningHub. Use photos you have the right to use, and ask the people in them - The key: it sits in \`API Setup\` and travels in every request, so take it out before you share the workflow - Credentials: the JSON holds none, and nothing from its author’s account ## README ```markdown # Pose transfer from a reference photo with upscaling An n8n workflow with an upload form for two pictures: a photo of a person and a picture of a pose. A RunningHub AI app redraws the person in that pose, and a second app enlarges the result until its shorter side is 1440 pixels. Every step runs on RunningHub, through its API. ## What is inside - `workflow.json`: the workflow as n8n exports it, 22 nodes and no sticky notes. It holds no credential. - `README.md`: these notes. ## What we changed from the original copy - The key's placeholder in `API Setup` was `YOUR_RUNNINGHUB_API`. It is now `YOUR_RUNNINGHUB_API_KEY`, so it says what goes there. Nothing else changed. ## Before you start - An n8n instance, on n8n Cloud or your own server. - A RunningHub account with a balance, and its API key. Both apps run as paid tasks there. ## Set it up 1. In n8n, create a workflow, open its menu and choose Import from File. Pick `workflow.json`. 2. Open `API Setup` and replace `YOUR_RUNNINGHUB_API_KEY` with your RunningHub key. Every RunningHub call reads it from there, so it is the only place to change. 3. Save, press Execute workflow and upload two pictures in the test form that opens. 4. Publish the workflow when you want the form's lasting address. ## How a run goes 1. `On form submission` takes two required files, `Upload Original Image` and `Upload Pose Image`, as JPG, PNG or WebP. 2. `getBinaryFile` passes both files on in one item. `uploadOriginalCharacter` and `uploadPostureDiagram` send them to RunningHub's `/task/openapi/upload` side by side, and each gets back a stored `fileName`. 3. `Merge` and `Aggregate` wait for both uploads. `createTask` then starts the RunningHub AI app `1986280816420552706` at `/task/openapi/ai-app/run`. Its node 23 gets the person, node 41 the pose and node 34 the instruction, which asks for the person in the first picture to take the pose in the second. 4. `Wait` pauses a minute and a half before `checkStatus` asks for the task's state. `Switch` sends `QUEUED` and `RUNNING` to `Wait1`, which checks again every minute, and `SUCCESS` on to `getOutput`. 5. `getOutput` reads the result's address, `downloadImage` fetches the picture, and `uploadNewImage` sends it back to RunningHub as a new file. 6. `createUpscaleTask` starts the second app, `1961632883674955778`, with that file in node 3 and `1440` in node 15, the length of the shorter side. 7. `Wait2` pauses a minute, `checkStatus1` asks again, and `Switch1` loops through `Wait3` every 30 seconds until the task is done. 8. `getOutput1` reads the address, and `downloadFinalImage` fetches the finished picture as a file in n8n. ## Change the look - The instruction: the `text` value in `createTask`'s JSON body. Say more about the clothes, the background or the framing if the result drifts. - The final size: `1440` in `createUpscaleTask`, the shorter side in pixels. - The apps: `webappId` in `createTask` and `createUpscaleTask`. The `nodeId` numbers belong to each app, so check them on the app's page in RunningHub when you swap one. - How long it waits: `Wait` (90 seconds), `Wait1` and `Wait2` (one minute each) and `Wait3` (30 seconds). ## Good to know - The picture stays in n8n. No node shows it on the form or saves it anywhere, so open `downloadFinalImage` under Executions to download it. To keep each one, add a Google Drive, Dropbox or email node after `downloadFinalImage`. - A failed task stops the run quietly: `Switch` and `Switch1` have nothing on their first output, `FAILED`. Any state they do not test ends the run with an error. - RunningHub bills both tasks to your account, the pose change and the enlargement. - Once the workflow is published, anyone with the form's address can start a run on your RunningHub balance. - Both pictures go to RunningHub, and so does the result before it is enlarged. Use only photos you have the right to use, and ask the people in them first. - The RunningHub key sits in `API Setup` and travels in each request's body, so take it out before you share the workflow. ``` ## What is in it 2 files, 23 KB, downloaded as a zip. ```text README.md 4 KB workflow.json 19 KB ``` ## Workflow check Checked by Mindket on 13 Nov 2026. Read from the workflow’s file, not from a run. - Steps: 22 steps, starting on a form - AI: No step calls an AI model - Sign-ins: Signs in to: RunningHub - 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 8 of its step types ## Get it - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/910aec2a-cfde-4056-b54b-3e9df8081c28) - [Its page on Mindket](https://mindket.com/p/910aec2a-cfde-4056-b54b-3e9df8081c28)