Pose changer API
AI pose changer API
Turn one on-model photo into a full set: the same person, outfit, place and light in a back view, a side view, walking or seated. Send the real back of the garment and the back view follows it.
Test keys are free and need no pack.
- 8 ready poses, a pose in words, or a photo of the pose to copy.
- Full body, knee up or waist up.
- Up to 2 photos of the garment's real back for true back views.



{
"poses": [
"walking",
"side"
],
"framing": "full"
}One request
Every request is asynchronous: the request returns a job in about two seconds, the images follow in 20 to 90 seconds by webhook or by polling.
curl https://api.garmo.studio/v1/edit/pose \
-H "Authorization: Bearer $GARMO_API_KEY" \
-H "Idempotency-Key: $(uuidgen)" \
-H "Content-Type: application/json" \
-d '{
"image_url": "https://shop.example/products/jacket-7-on-model.jpg",
"poses": [
"walking",
"side"
],
"framing": "full"
}'const r = await fetch("https://api.garmo.studio/v1/edit/pose", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.GARMO_API_KEY}`,
"Idempotency-Key": "order-123-pose",
"Content-Type": "application/json",
},
body: JSON.stringify({"image_url": "https://shop.example/products/jacket-7-on-model.jpg", "poses": ["walking", "side"], "framing": "full"}),
});
const job = await r.json();
console.log(job.id, job.status);import os, requests
r = requests.post(
"https://api.garmo.studio/v1/edit/pose",
headers={"Authorization": f"Bearer {os.environ['GARMO_API_KEY']}", "Idempotency-Key": "order-123-pose"},
json={
"image_url": "https://shop.example/products/jacket-7-on-model.jpg",
"poses": ["walking", "side"],
"framing": "full",
},
)
job = r.json()
print(job["id"], job["status"])<?php
$ch = curl_init("https://api.garmo.studio/v1/edit/pose");
curl_setopt_array($ch, [
CURLOPT_RETURNTRANSFER => true,
CURLOPT_POST => true,
CURLOPT_POSTFIELDS => json_encode(["image_url" => "https://shop.example/products/jacket-7-on-model.jpg", "poses" => ["walking", "side"], "framing" => "full"]),
CURLOPT_HTTPHEADER => ["Authorization: Bearer " . getenv("GARMO_API_KEY"), "Idempotency-Key: order-123-pose", "Content-Type: application/json"],
]);
$job = json_decode(curl_exec($ch), true);
echo $job["id"], " ", $job["status"];require "net/http"
require "json"
uri = URI("https://api.garmo.studio/v1/edit/pose")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer #{ENV.fetch("GARMO_API_KEY")}"
req["Idempotency-Key"] = "order-123-pose"
req["Content-Type"] = "application/json"
req.body = <<~'JSON'
{
"image_url": "https://shop.example/products/jacket-7-on-model.jpg",
"poses": [
"walking",
"side"
],
"framing": "full"
}
JSON
res = Net::HTTP.start(uri.host, uri.port, use_ssl: true) { |http| http.request(req) }
job = JSON.parse(res.body)
puts job["id"], job["status"]package main
import (
"fmt"
"io"
"net/http"
"os"
"strings"
)
func main() {
body := strings.NewReader(`{
"image_url": "https://shop.example/products/jacket-7-on-model.jpg",
"poses": [
"walking",
"side"
],
"framing": "full"
}`)
req, _ := http.NewRequest("POST", "https://api.garmo.studio/v1/edit/pose", body)
req.Header.Set("Authorization", "Bearer "+os.Getenv("GARMO_API_KEY"))
req.Header.Set("Idempotency-Key", "order-123-pose")
req.Header.Set("Content-Type", "application/json")
res, err := http.DefaultClient.Do(req)
if err != nil {
panic(err)
}
defer res.Body.Close()
out, _ := io.ReadAll(res.Body)
fmt.Println(res.Status, string(out))
}import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
public class Garmo {
public static void main(String[] args) throws Exception {
String body = """
{
"image_url": "https://shop.example/products/jacket-7-on-model.jpg",
"poses": [
"walking",
"side"
],
"framing": "full"
}
""";
HttpRequest req = HttpRequest.newBuilder(URI.create("https://api.garmo.studio/v1/edit/pose"))
.header("Authorization", "Bearer " + System.getenv("GARMO_API_KEY"))
.header("Idempotency-Key", "order-123-pose")
.header("Content-Type", "application/json")
.POST(HttpRequest.BodyPublishers.ofString(body))
.build();
HttpResponse<String> res = HttpClient.newHttpClient().send(req, HttpResponse.BodyHandlers.ofString());
System.out.println(res.statusCode() + " " + res.body());
}
}{
"id": "job_8Kq2xV7mPz4LtR9wNc3B",
"object": "job",
"tool": "pose",
"status": "completed",
"livemode": true,
"outputs": [
{
"id": "out_1",
"status": "succeeded",
"label": "Walking",
"url": "https://….r2.cloudflarestorage.com/renders/2026/11/8f3c…0.webp?X-Amz-Signature=…",
"url_expires_at": "2026-11-20T14:00:00Z"
},
{
"id": "out_2",
"status": "succeeded",
"label": "Side",
"url": "https://….r2.cloudflarestorage.com/renders/2026/11/8f3c…1.webp?X-Amz-Signature=…",
"url_expires_at": "2026-11-20T14:00:00Z"
}
],
"credits_charged": 2,
"credits_refunded": 0,
"metadata": {
"sku": "DR-123"
},
"created_at": "2026-11-19T14:02:11Z",
"completed_at": "2026-11-19T14:02:58Z"
}Parameters
poses | Pose ids from GET /catalog/poses. |
framing | How much of the model is in frame. |
description | A pose of your own in words (up to 200 characters). |
pose_image_url | A photo of someone in the pose you want; only the pose is copied (or pose_image_base64, pose_image_upload_id). |
back_image_urls | Up to 2 photos of the real back of the garment, so a back view is true to it. |
Cost
1 credit per pose
1 API credit = 1 image. Failed and canceled images are refunded automatically.
API pricingWhat people build with it
A full product gallery
Front, side, back and a walking shot for every product page from one photo.
Fit and drape
A walking shot shows how a dress moves; a side view shows a coat's length.
Consistent catalogs
The same set of poses for every product, made the same way.
Questions, answered.
What developers ask before connecting Garmo to a shop or a workflow.
Still stuck? Email usDoes the model's face stay the same?
Yes. The face, hair, skin tone and body come from your photo, and every garment is reproduced: color, fabric, print, logo and buttons.
How does it know the back of the garment?
It can only guess from the front. Send up to two photos of the real back in back_image_urls and the back view copies them.
What does it cost?
One credit per pose: four poses make four images.
Other edits in the API
POST /generateClothes color changer APIEvery colorway from one photo, to the exact hex.POST /edit/colorModel swap APIThe same outfit and pose on another model.POST /edit/model-swapGhost mannequin APIThe invisible-mannequin shot, without the mannequin.POST /edit/ghost-mannequinBackground changer APIKeep the subject, change the place, match the light.POST /edit/backgroundBackground remover APICut out products onto transparent, white or a brand color.POST /edit/remove-backgroundImage upscaler API2K or 4K product photos with real material detail.POST /edit/upscaleGet an API key
Test keys are free and need no pack.




