Meshy V7 Multi Image To 3d API Documentation

Meshy V7 Multi Image To 3d API Documentation

Playground

Meshy V7 Multi-Image-to-3D reconstructs textured, PBR-ready 3D models from one to four views of the same object, with configurable topology, rigging, and animation options for game assets, product visualization, 3D design, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Meshy V7 Multi-Image to 3D reconstructs a textured 3D mesh from one to four images of the same object taken from different angles. It generates a GLB model and provides additional export formats such as FBX, OBJ, and USDZ when available.

Why Choose This?

• Multi-image 3D reconstruction
  Generate a 3D model from one to four reference images of the same object.

• Better shape consistency
  Use multiple views to improve object structure, silhouette, and spatial accuracy compared with single-image generation.

• Texture generation
  Generate textured 3D models with optional PBR material output.

• Geometry controls
  Adjust topology, target polygon count, symmetry mode, and remeshing behavior for different production needs.

• Optional rigging and animation
  Enable humanoid auto-rigging and animation presets when supported by the input object.

• Multiple export formats
  Receive GLB output with available FBX, OBJ, and USDZ exports.

Parameters

How to Use

1. Upload reference images — Provide one to four images of the same object from different angles.
2. Configure geometry — Adjust topology, target polygon count, symmetry mode, or remeshing when needed.
3. Configure textures — Use should_texture, enable_pbr, texture_prompt, or texture_image_url to control material output.
4. Enable rigging — Use enable_rigging for suitable humanoid characters and optionally specify rigging_height_meters.
5. Enable animation — Use enable_animation and select an animation_action_id when an animation preset is needed. Rigging must also be enabled.
6. Submit — Generate the 3D model and download the available exports.

Pricing

Example Costs

Best Use Cases

• Multi-view object reconstruction — Build 3D models from front, side, rear, or angled object views.
• Product 3D assets — Convert product photos into textured 3D models for previews and visualization.
• E-commerce workflows — Create 3D assets for interactive product display.
• Game and real-time assets — Generate usable 3D models with geometry and remeshing controls.
• Character workflows — Generate textured character models with optional rigging and animation.
• Prototype modeling — Turn multiple concept views into a 3D asset for iteration.

Pro Tips

• Use clear, consistent photos of the same object.
• Provide front, side, and rear views when possible.
• Keep lighting, background, and object scale consistent across images.
• Do not mix different objects or different versions of the same object.
• Avoid strong reflections, motion blur, occlusion, or heavy shadows.
• Use texture_prompt to describe material details such as metal, fabric, leather, ceramic, or plastic.
• Enable rigging only for suitable humanoid characters.
• Use Meshy V7 Image to 3D when you only have one reference image.

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"
  ],
  "topology": "triangle",
  "target_polycount": 30000,
  "symmetry_mode": "auto",
  "should_remesh": true,
  "should_texture": true,
  "enable_pbr": false,
  "pose_mode": "",
  "enable_rigging": false,
  "rigging_height_meters": 1.7,
  "enable_animation": false,
  "animation_action_id": 92
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/meshy/v7/multi-image-to-3d" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters