Docs / image / Qwen Image 3.0 Image to Image
Qwen Image 3.0 Image to Image online
Edit and restyle images with Qwen Image 3.0 using plain-language instructions.
Rp Rp510 / gambar
qwen3/image-to-image model id
1 · Create a task
Kirim permintaan untuk membuat tugas generasi image. Wajib header Idempotency-Key. Saldo direservasi sebesar estimasi; task gagal tidak ditagih.
curl -X POST https://getrun.id/v1/tasks \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Idempotency-Key: my-task-001" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3/image-to-image",
"input": {
"prompt": "Preserve the entire coffee shop environment, furniture, lighting, customers, wall texture, poster frame, and camera perspective.\nReplace only the content of the framed poster.\nTransform the poster into a clean visual showcase featuring:\n“Qwen Image 3.0 API”\n“Kie.ai”\nInclude a few realistic generated images inside the poster: a portrait photograph, a landscape scene, and an artistic illustration.\nKeep the design simple with minimal text and a professional editorial style.\nDo not add futuristic technology elements, glowing effects, abstract AI symbols, or large amounts of text.\nMaintain realistic lighting, reflections, and physical integration with the coffee shop environment.\nRealistic interior photography",
"image_size": "16:9",
"image_urls": [
"https://example.com/input.jpg"
],
"resolution": "1K",
"output_format": "png"
}
}'const res = await fetch('https://getrun.id/v1/tasks', {
method: 'POST',
headers: {
Authorization: 'Bearer YOUR_API_KEY',
'Idempotency-Key': 'my-task-001',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "qwen3/image-to-image",
"input": {
"prompt": "Preserve the entire coffee shop environment, furniture, lighting, customers, wall texture, poster frame, and camera perspective.\nReplace only the content of the framed poster.\nTransform the poster into a clean visual showcase featuring:\n“Qwen Image 3.0 API”\n“Kie.ai”\nInclude a few realistic generated images inside the poster: a portrait photograph, a landscape scene, and an artistic illustration.\nKeep the design simple with minimal text and a professional editorial style.\nDo not add futuristic technology elements, glowing effects, abstract AI symbols, or large amounts of text.\nMaintain realistic lighting, reflections, and physical integration with the coffee shop environment.\nRealistic interior photography",
"image_size": "16:9",
"image_urls": [
"https://example.com/input.jpg"
],
"resolution": "1K",
"output_format": "png"
}
}),
});
const task = await res.json();import requests
res = requests.post(
"https://getrun.id/v1/tasks",
headers={
"Authorization": "Bearer YOUR_API_KEY",
"Idempotency-Key": "my-task-001",
},
json={
"model": "qwen3/image-to-image",
"input": {
"prompt": "Preserve the entire coffee shop environment, furniture, lighting, customers, wall texture, poster frame, and camera perspective.\nReplace only the content of the framed poster.\nTransform the poster into a clean visual showcase featuring:\n“Qwen Image 3.0 API”\n“Kie.ai”\nInclude a few realistic generated images inside the poster: a portrait photograph, a landscape scene, and an artistic illustration.\nKeep the design simple with minimal text and a professional editorial style.\nDo not add futuristic technology elements, glowing effects, abstract AI symbols, or large amounts of text.\nMaintain realistic lighting, reflections, and physical integration with the coffee shop environment.\nRealistic interior photography",
"image_size": "16:9",
"image_urls": [
"https://example.com/input.jpg"
],
"resolution": "1K",
"output_format": "png"
}
},
)
task = res.json()Input parameters
| Name | Type | Required | Description | Example |
|---|---|---|---|---|
seed |
integer | No | The random seed. Value range: [0, 2147483647]. A fixed seed helps maintain relatively stable results. (min 0, max 2147483647) | 1 |
prompt |
string | Yes | The positive prompt that describes the image content, style, and composition you want to generate or edit. Both Chinese and English are supported. (max 5000 chars) | Preserve the entire coffee shop environment, f |
image_size |
string | No | The output image size. Opsi: 1:1 3:2 2:3 4:3 3:4 16:9 9:16 21:9 |
16:9 |
image_urls |
array | Yes | Gambar yang diedit, maksimal 3. (array of file URLs) | https://example.com/input.jpg |
resolution |
string | No | The output image resolution. Opsi: 1K 2K |
1K |
nsfw_checker |
boolean | No | A configurable parameter. Defaults to true in the Playground. | true |
output_format |
string | No | Generate image format Opsi: png jpeg |
png |
prompt_extend |
boolean | No | Whether to enable intelligent prompt rewriting. Default: true (recommended). When enabled, the model optimizes the positive prompt, which significantly improves results for simple descriptions. | true |
negative_prompt |
string | No | The negative prompt that describes content you do not want to appear in the image. (max 5000 chars) | — |
2 · Poll the result
Ambil status tugas hingga selesai — poll tiap 2–5 detik.
Respons saat sukses:
{
"id": "task_9f2c…",
"status": "succeeded",
"model": "qwen3/image-to-image",
"price": {
"currency": "IDR",
"estimated": 510,
"reserved": 510,
"final": 510
},
"output": {
"urls": [
"https://storage.getcore.id/outputs/task_9f2c…/0.png"
],
"expires_at": "(7 hari setelah selesai)"
}
}
Status values
| Status | Keterangan |
|---|---|
queued | Tugas sedang diantrikan. |
processing | Sedang diproses. |
succeeded | Berhasil. |
failed | Gagal — lihat error detail, tidak ditagih. |
image/png, dilayani dari CDN kami dan berlaku 7 hari — salin ke penyimpananmu sendiri untuk jangka panjang.Best practices
Bila generation gagal, task berstatus failed dengan error.code ternormalisasi (mis. moderation_blocked, upstream_error) dan price.final = 0 — saldo dikembalikan otomatis. Daftar lengkap kode error ada di Error handling. Selalu kirim Idempotency-Key unik per tugas agar retry aman.
Coba tanpa kode: jalankan model ini langsung dari Playground atau lihat di API Market.
