Qwen Image Edit Multiple Angles API Documentation

Qwen Image Edit Multiple Angles API Documentation

Playground

Generate specific camera angles from a single image using a 96-pose camera system. Control horizontal rotation, vertical tilt, and zoom to create front, side, back views and more. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Qwen-Image-Edit Multiple Angles transforms a single input image into any camera angle using an advanced 96-pose camera system. Generate front views, side profiles, back views, bird’s-eye shots, and dramatic low angles — all from one photo.

Perfect for e-commerce product photography, 3D asset creation, character design, virtual try-on, and creative content generation.

Why Choose Multiple Angles?

• Single Image to Multi-View Upload one photo and generate any angle — no need for multiple photo shoots or 3D modeling.

• 96-Pose Camera System 8 horizontal angles × 4 vertical angles × 3 distance levels = comprehensive viewpoint coverage.

• Intuitive Angle Control Specify angles in degrees — the system automatically optimizes for the best results.

• Production-Ready API No cold starts, fast inference, and predictable pricing for seamless integration.

Camera System Reference

Horizontal Angle (Azimuth) — Rotate Around Subject

Accepts any value 0-359° and rounds to the nearest optimal angle.

Vertical Angle (Elevation) — Camera Height

Accepts any value -30° to 60° and rounds to the nearest optimal angle.

Distance — Zoom Level

Parameters

Use Cases

E-Commerce Product Views

Generate 360° product views from a single photo for online stores.

{
 "images": ["https://example.com/product.jpg"],
 "horizontal_angle": 90,
 "vertical_angle": 0,
 "distance": 1
}

Character Design & Concept Art

Create character turnarounds for animation and game development.

{
 "images": ["https://example.com/character.jpg"],
 "horizontal_angle": 180,
 "vertical_angle": 0,
 "distance": 1
}

Dramatic Photography Effects

Generate cinematic angles for creative content.

{
 "images": ["https://example.com/portrait.jpg"],
 "horizontal_angle": 45,
 "vertical_angle": -30,
 "distance": 0
}

Aerial & Bird’s-Eye Views

Create top-down perspectives for real estate or product layouts.

{
 "images": ["https://example.com/scene.jpg"],
 "horizontal_angle": 0,
 "vertical_angle": 60,
 "distance": 2
}

Best Practices

1. Use clear, well-lit input images for best multi-angle results.
2. Start with eye-level (0°) vertical angle for natural-looking outputs.
3. Use medium distance (1) as baseline, then adjust for tighter or wider framing.
4. Add prompts for additional style guidance beyond angle transformation.
5. Test with 90° or 180° horizontal rotations first to understand subject handling.

Pricing

$0.025 per generated image

Related Models

• Qwen Image Edit 2511 — General-purpose AI image editing.
• Qwen Image Edit Plus — High-fidelity image editing with enhanced detail retention.

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-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
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters