Capability · Ghost mannequin

Ghost mannequin API untuk foto produk hollow-man

Ringkasan singkat

API ghost mannequin Photta memproses foto pakaian pada manekin dan mengembalikan gambar invisible-mannequin dengan bagian dalam pakaian yang direkonstruksi. Pilih gaya 3d atau flat_lay, POST, lakukan polling setiap 3 detik, unduh setelah completed.

Dapatkan API key Baca dokumentasi

Waktu umum: 1.5–4 min
Credits: 4 credits pada 2K · 5 credits pada 4K
Pemrosesan: async, polling
Batasan: 600 requests/min
Autentikasi: Bearer key

Setiap angka di halaman ini bersumber dari dokumentasi API Photta · diperiksa 2026-09-10

POST/api/v1/ghost-mannequin

RESPONSE=$(curl -s -X POST https://api.photta.app/api/v1/ghost-mannequin \
  -H "Authorization: Bearer $PHOTTA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "product_image": "https://cdn.yourstore.com/products/jacket-front.jpg",
  "back_image": "https://cdn.yourstore.com/products/jacket-back.jpg",
  "image_side": "front",
  "angle": "side",
  "style": "3d",
  "background_color": "white",
  "resolution": "2K",
  "aspect_ratio": "3:4",
  "user_instruction": "closed front, cream interior lining",
  "brand_label_id": "7cc9f988-068b-44cd-8004-22f486b10e67"
}')
ID=$(echo "$RESPONSE" | jq -r '.data.id')

const res = await fetch("https://api.photta.app/api/v1/ghost-mannequin", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.PHOTTA_API_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({
    "product_image": "https://cdn.yourstore.com/products/jacket-front.jpg",
    "back_image": "https://cdn.yourstore.com/products/jacket-back.jpg",
    "image_side": "front",
    "angle": "side",
    "style": "3d",
    "background_color": "white",
    "resolution": "2K",
    "aspect_ratio": "3:4",
    "user_instruction": "closed front, cream interior lining",
    "brand_label_id": "7cc9f988-068b-44cd-8004-22f486b10e67"
  }),
});
const { data } = await res.json(); // data.id, data.status

import os, requests

res = requests.post(
    "https://api.photta.app/api/v1/ghost-mannequin",
    headers={"Authorization": f"Bearer {os.environ['PHOTTA_API_KEY']}"},
    json={
      "product_image": "https://cdn.yourstore.com/products/jacket-front.jpg",
      "back_image": "https://cdn.yourstore.com/products/jacket-back.jpg",
      "image_side": "front",
      "angle": "side",
      "style": "3d",
      "background_color": "white",
      "resolution": "2K",
      "aspect_ratio": "3:4",
      "user_instruction": "closed front, cream interior lining",
      "brand_label_id": "7cc9f988-068b-44cd-8004-22f486b10e67"
    },
)
data = res.json()["data"]  # data["id"], data["status"]

A garment shown without its mannequin by the ghost mannequin API — Contoh output

Sekilas

Endpoint: POST /api/v1/ghost-mannequin
Autentikasi: API key Bearer
Pemrosesan: Asinkron — lakukan polling ke endpoint status
Waktu umum: 1.5–4 min
Credits: 4 credits pada 2K · 5 credits pada 4K
Rasio aspek: 3:4 · 1:1 · 4:3 · 9:16 · 16:9
Batas input: Hingga 10 MB per gambar; JPEG, PNG, WebP
Idempoten: Tidak

Request dan response

Request

RESPONSE=$(curl -s -X POST https://api.photta.app/api/v1/ghost-mannequin \
  -H "Authorization: Bearer $PHOTTA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "product_image": "https://cdn.yourstore.com/products/jacket-front.jpg",
  "back_image": "https://cdn.yourstore.com/products/jacket-back.jpg",
  "image_side": "front",
  "angle": "side",
  "style": "3d",
  "background_color": "white",
  "resolution": "2K",
  "aspect_ratio": "3:4",
  "user_instruction": "closed front, cream interior lining",
  "brand_label_id": "7cc9f988-068b-44cd-8004-22f486b10e67"
}')
ID=$(echo "$RESPONSE" | jq -r '.data.id')

const res = await fetch("https://api.photta.app/api/v1/ghost-mannequin", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.PHOTTA_API_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({
    "product_image": "https://cdn.yourstore.com/products/jacket-front.jpg",
    "back_image": "https://cdn.yourstore.com/products/jacket-back.jpg",
    "image_side": "front",
    "angle": "side",
    "style": "3d",
    "background_color": "white",
    "resolution": "2K",
    "aspect_ratio": "3:4",
    "user_instruction": "closed front, cream interior lining",
    "brand_label_id": "7cc9f988-068b-44cd-8004-22f486b10e67"
  }),
});
const { data } = await res.json(); // data.id, data.status

import os, requests

res = requests.post(
    "https://api.photta.app/api/v1/ghost-mannequin",
    headers={"Authorization": f"Bearer {os.environ['PHOTTA_API_KEY']}"},
    json={
      "product_image": "https://cdn.yourstore.com/products/jacket-front.jpg",
      "back_image": "https://cdn.yourstore.com/products/jacket-back.jpg",
      "image_side": "front",
      "angle": "side",
      "style": "3d",
      "background_color": "white",
      "resolution": "2K",
      "aspect_ratio": "3:4",
      "user_instruction": "closed front, cream interior lining",
      "brand_label_id": "7cc9f988-068b-44cd-8004-22f486b10e67"
    },
)
data = res.json()["data"]  # data["id"], data["status"]

202 Accepted / Completed

{
  "data": {
    "id": "gm_d4e5f6",
    "status": "processing",
    "style": "3d",
    "angle": "side",
    "background_color": "white",
    "resolution": "2K",
    "aspect_ratio": "3:4",
    "credits_used": 4,
    "created_at": "2026-04-10T16:00:00Z"
  },
  "request_id": "req_gm001"
}

{
  "data": {
    "id": "gm_d4e5f6",
    "status": "completed",
    "style": "3d",
    "angle": "side",
    "background_color": "white",
    "resolution": "2K",
    "aspect_ratio": "3:4",
    "output_url": "https://cdn.photta.app/generated/gm_d4e5f6.jpg",
    "thumbnail_url": "https://cdn.photta.app/generated/gm_d4e5f6-thumb.jpg",
    "credits_used": 4,
    "created_at": "2026-04-10T16:00:00Z",
    "completed_at": "2026-04-10T16:00:48Z",
    "duration_ms": 48000
  },
  "request_id": "req_gm002"
}

Parameter request

FieldDeskripsi

product_image

Tipe: stringWajib

URL or base64 data URI of the garment photo (front or back, on a mannequin or flat).

back_image

Tipe: string

URL or base64 data URI of the opposite side — helps the AI reconstruct the interior of the garment for a more realistic 3D effect.

image_side

Tipe: string

Which side product_image represents.

= front

frontback

angle

Tipe: string

Camera angle for the output. "side" is worth calling out: the side view is reconstructed from the front photo (plus the back photo when provided), giving you a third catalog view without a third photoshoot — and it works well even on textured garments (crochet, lace, embroidery).

= straight

straightbackside

style

Tipe: string

Output style: "3d" (ghost mannequin with 3D body shape) or "flat_lay" (garment laid flat, mannequin removed).

= 3d

3dflat_lay

background_color

Tipe: string

Background color.

= white

whitegraybeigeblack

resolution

Tipe: string

Output resolution. "2K" costs 4 credits per image; "4K" costs 5 credits per image. 4K is produced natively in a single generation — pick it upfront; the resolution cannot be changed after creation. Note: 4K cannot be combined with aspect_ratio 1:1 — that combination returns 400.

= 2K

2K4K

aspect_ratio

Tipe: string

Output aspect ratio. Note: 1:1 is not available at 4K resolution — 1:1 combined with 4K returns 400.

= 3:4

3:41:14:39:1616:9

user_instruction

Tipe: string

Optional free-form note, max 400 characters (anything longer is silently truncated). A guarded steer for ambiguous rendering choices — e.g. "closed front", "cream interior lining", "buttoned up" — it never overrides the source garment, brand label, or structural reconstruction, and it is explicitly NOT a determinism/seed control.

brand_label_id

Tipe: string

Brand label UUID returned by the Brand Labels API. Applied to the generated garment when present. API v1 request fields use snake_case; use brand_label_id.

Error

StatusTipeArti

400invalid_request_error: The request is malformed or contains invalid parameters.
401authentication_error: The API key is missing, invalid, or expired.
402insufficient_credits_error: Your account does not have enough credits.
404not_found_error: The requested resource does not exist.
409conflict_error: The request conflicts with current state — e.g. your concurrent-batch cap is reached.
429rate_limit_error: Too many requests. Slow down and retry.Retry-After: 30
500api_error: An internal server error occurred. Retry later.

Batasan

600 request per menit per API key (Fixed window; batasannya sama di setiap paket)
Respons 429 menyertakan Retry-After: 30 detik
Hingga 10 MB per gambar
Format: JPEG, PNG, WebP
Batch konkuren per paket: Free 1 · Hobby 2 · Seller 3 · Brand 4 · Studio 6
Hanya polling — API tidak mengirim webhook.

Satu foto masuk, satu foto invisible-mannequin keluar

Unggah sumber, pilih gaya, kirim, lakukan polling, unduh.

Langkah 1
Buat API key
Ghost mannequin menggunakan kredensial yang sama dengan setiap kapabilitas Photta lainnya — satu kunci, satu saldo credits.
Langkah 2
Unggah foto sumber
Kirim URL publik atau base64 data URI di `product_image`; tambahkan `back_image` jika Anda memiliki tampilan belakang. JPEG, PNG, dan WebP hingga 10 MB per gambar.
Langkah 3
POST job ghost mannequin
POST ke `/api/v1/ghost-mannequin` dengan `product_image`, `style` (`3d` atau `flat_lay`), serta `angle`, `background_color`, `resolution` opsional. Polling adalah satu-satunya sinyal penyelesaian — API tidak mengirim webhook.
Langkah 4
Lakukan polling hingga job selesai
GET `/api/v1/ghost-mannequin/:id` setiap 3 detik hingga `data.status` bernilai `completed` atau `failed`; penyelesaian tipikal adalah 1.5 hingga 4 menit.
Langkah 5
Unduh dan simpan secara persisten
Output berupa PNG dengan manekin yang dihapus dan bagian dalam pakaian direkonstruksi. Ideal untuk foto ghost PDP, galeri produk bernuansa 3D, dan sisipan flat-lay.

Endpoint yang sama di Node.js, Python, dan cURL

Pertanyaan yang diajukan developer sebelum merilis ghost mannequin

Apa itu fotografi ghost mannequin?

Perlakuan PDP di mana pakaian tampak melayang pada tubuh tak terlihat, menampilkan bentuk dan konstruksi interior secara bersamaan. Secara historis ini digabungkan dari beberapa jepretan studio; API Photta menghasilkannya dalam satu panggilan dari satu foto pada manekin.

Berapa biaya ghost mannequin?

4 credits pada 2K, 5 credits pada 4K — satu credit lebih murah di setiap tier dibandingkan try-on. Job yang gagal otomatis di-refund.

Apa perbedaan antara gaya 3D dan flat-lay?

Gaya `3d` mempertahankan bentuk tubuh tiga dimensi dari manekin — pakaian mempertahankan volume, bahu dan lengan terlihat alami, dan bagian dalam direkonstruksi. `flat_lay` meratakan pakaian menjadi tata letak 2D yang rapi, ideal untuk koleksi kapsul atau listing marketplace yang membutuhkan bentuk tampak depan yang konsisten.

Bisakah saya memproses banyak foto secara batch?

Ya. POST ke `/api/v1/ghost-mannequin/batch` dengan array gambar sumber. Respons memberi Anda batch ID ditambah generation ID per item. Lakukan polling ke `/api/v1/ghost-mannequin/batch/:id` untuk status agregat atau setiap item secara individual.

Apakah ini mempertahankan jahitan dan label interior?

Ya — model merekonstruksi bagian dalam pakaian (bagian dalam kerah, bagian dalam manset, lapisan ban pinggang) alih-alih melakukan halusinasi permukaan generik. Tag dan label cetak yang terlihat pada foto asli dipertahankan jika memungkinkan.

Bagaimana cara melakukan polling untuk hasilnya?

GET `/api/v1/ghost-mannequin/:id` setiap 3 detik. Job batch melakukan polling ke endpoint induk yang mengembalikan status agregat beserta rincian per item.

Kapabilitas terkait

Setiap angka di halaman ini bersumber dari dokumentasi API Photta · diperiksa 2026-09-10

Coba API dalam lima menit

Buat Photta API key, tempel cuplikan cURL di atas, dan Anda akan mendapatkan gambar on-model pertama sebelum kopi selesai diseduh.

Buat akun dan dapatkan API key Baca dokumentasi

1.5–4 min
4 credits pada 2K · 5 credits pada 4K
async, polling
600 requests/min
Bearer key

Ghost mannequin API untuk foto produk hollow-man

Sekilas

Request dan response

Parameter request

Error

Satu foto masuk, satu foto invisible-mannequin keluar

Buat API key

Unggah foto sumber

POST job ghost mannequin

Lakukan polling hingga job selesai

Unduh dan simpan secara persisten

Endpoint yang sama di Node.js, Python, dan cURL

Pertanyaan yang diajukan developer sebelum merilis ghost mannequin

Kapabilitas terkait

Coba API dalam lima menit