Qwen Image Edit 2509 Multiple Angles API Documentation
Playground
Try it on WaveSpeedAI!Qwen Image Edit 2509 Multiple Angles is an AI image editing model that generates multiple-angle views of objects or scenes from a single image. Transform perspectives and create diverse viewpoints with text prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Qwen Image Edit 2509 Multiple Angles generates new camera perspectives of a subject from reference images. Control horizontal rotation, vertical tilt, and camera distance to create realistic multi-angle views — perfect for product photography and 3D visualization without reshooting.
Why Choose This?
-
Multi-angle generation Create new camera perspectives from up to 3 reference images.
-
Precise horizontal rotation Rotate the viewpoint in 5 positions: -90 (left), -45, 0 (front), 45, 90 (right).
-
Vertical tilt control Adjust camera elevation: -30 (low angle), 0 (eye level), 30 (elevated), 60 (high angle).
-
Camera distance Control zoom level: 0 = close-up, 1 = medium shot, 2 = wide shot.
-
Optional prompt guidance Add text descriptions to refine the generated perspective.
Parameters
| Parameter | Required | Description |
|---|---|---|
| images | Yes | Reference images, up to 3 (click ”+ Add Item”) |
| horizontal_angle | No | Horizontal rotation: -90, -45, 0, 45, 90 (default: 90) |
| vertical_angle | No | Vertical tilt: -30, 0, 30, 60 (default: 0) |
| distance | No | Camera distance: 0 (close-up), 1 (medium), 2 (wide) (default: 1) |
| prompt | No | Text description to guide the output |
| size | No | Custom output size |
| seed | No | Random seed for reproducibility (-1 for random) |
| output_format | No | Output format: jpeg (default), png, webp |
| enable_base64_output | No | Return BASE64 string instead of URL (API only) |
| enable_sync_mode | No | Wait for result before returning response (API only) |
Angle Reference
Horizontal Angle (horizontal_angle):
- -90 → left side view
- -45 → rotate left 45 degrees
- 0 → front view
- 45 → rotate right 45 degrees
- 90 → right side view
Vertical Angle (vertical_angle):
- -30 → low angle (looking up)
- 0 → eye level
- 30 → elevated view
- 60 → high angle (looking down)
Distance:
- 0 → close-up
- 1 → medium shot
- 2 → wide shot
How to Use
- Upload your images — provide 1-3 reference images.
- Set horizontal angle — choose the horizontal rotation.
- Set vertical angle (optional) — adjust camera elevation.
- Set distance (optional) — choose close-up, medium, or wide shot.
- Add prompt (optional) — describe any additional guidance.
- Run — submit and download the new perspective.
Pricing
| Output | Cost |
|---|---|
| Per image | $0.025 |
Best Use Cases
- Product Photography — Generate multiple product angles from a few reference shots.
- E-commerce — Produce multi-angle product listings without reshooting.
- 3D Visualization — Preview objects from different perspectives.
- Sports & Action — Create alternate viewing angles of action scenes.
- Creative Exploration — Experiment with camera angles and compositions.
Pro Tips
- Use multiple reference images from different angles for more accurate results.
- Combine horizontal rotation with vertical tilt for dynamic camera positions.
- Use distance 0 for detail shots, distance 2 for full-body or environment context.
- Values are rounded to the nearest valid angle automatically.
- Keep seed consistent to compare different angle settings on the same subject.
Notes
- Images is the only required field; maximum 3 reference images.
- Angle values are rounded to the nearest valid position.
- enable_base64_output and enable_sync_mode are API-only parameters.
- Ensure uploaded image URLs are publicly accessible.
- Seed value -1 generates a random seed each time.
Related Models
- Qwen Image Max Edit — Bilingual image editing with multi-image support.
- Qwen Image Max Text-to-Image — Generate images from text descriptions.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"horizontal_angle": 0,
"vertical_angle": 0,
"distance": 1,
"output_format": "jpeg"
}
JSON
)
# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
--connect-timeout 10 --max-time 60 \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/qwen-image/edit-2509-multiple-angles" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}"); then
printf 'Submit failed. %s\n' "${CHECK}" >&2
exit 1
fi
TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"
# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
# Transient errors (429, 5xx) are retried, honoring Retry-After.
HTTP_CODE=$(curl --silent --show-error --fail-with-body \
--connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
--output "${BODY_FILE}" --write-out '%{http_code}' \
"${RESULT_URL}" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
case "${HTTP_CODE}" in
2??) ;;
000|429|5??) # dropped connection or temporary error: keep polling
printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
sleep 10; continue ;;
*) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
cat "${BODY_FILE}" >&2; exit 1 ;;
esac
RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${STATUS}" in
completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted)
printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneRetry temporary errors only while polling, never the submit request. Errors, retries and timeouts
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| images | array<string> | Yes | - | 0 ~ 3 items | The input images. A maximum of 3 reference images can be uploaded. |
| horizontal_angle | integer | No | 0 | -90 ~ 90 | Horizontal rotation angle in degrees. Controls the camera's horizontal position. Negative values rotate left, positive values rotate right. Values are rounded to the nearest valid angle: -90 (left), -45 (rotate left), 0 (front), 45 (rotate right), 90 (right). |
| vertical_angle | integer | No | 0 | -30 ~ 60 | Vertical tilt angle (elevation) in degrees. Controls the camera's vertical position. Values are rounded to the nearest valid angle: -30 (low angle), 0 (eye level), 30 (elevated), 60 (high angle). |
| distance | integer | No | 1 | 0 ~ 2 | Camera distance/zoom level. 0 = close-up, 1 = medium shot, 2 = wide shot. |
| prompt | string | No | - | Optional additional prompt to guide the generation. This is appended to the angle prompt. | |
| size | string | No | - | 256 ~ 1536 | Advanced option. The size of the generated media in pixels (width*height). |
| seed | integer | No | - | - | The random seed to use for the generation. -1 means a random seed will be used. |
| output_format | string | No | jpeg | jpeg, png, webp | The format of the output image. |
Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Task status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses. |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Status: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |