Meshy Relief Image-to-3D API

meshy/relief

Meshy Relief converts photos into embossed or engraved 3D reliefs, making it suitable for decorative models, plaques, medallions, 3D printing, and design workflows, with support for standard 3D and depth-map outputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Image to 3D
Input

Drag & drop or click to upload

preview

ExamplesView all

3D

Related Models

README

Meshy Relief

Meshy Relief turns a photo into a relief: a flat plate with the subject raised (emboss) or cut in (engrave), for 3D printing and CNC workflows. Download a GLB, a binary STL in millimeters, and the 16-bit depth map.

Why Choose This?

  • Photo to relief — Create a relief model from one image.
  • Carving controls — Emboss or engrave, with depth, size and base thickness in millimeters.
  • Cut-out and bend — Remove the background plate, or curl the relief into a convex or concave arc.
  • Depth map only — Skip the model and get just the depth map at the same price.

Parameters

ParameterRequiredDescription
imageYesPhoto to convert (JPEG, PNG or WebP, at least 32 x 32 px, up to 20 MB).
variantNolow or high relief style; sets the default carving depth (3 mm or 6 mm). Default: low.
should_generate_modelNoSet to false to return only the depth map. Default: true.
size_mmNoLength of the photo's longer side on the model, 20-250 mm. Default: 60.
carving_modeNoemboss or engrave. Default: emboss.
carving_depth_mmNoCarving depth, 0-60 mm.
remove_baseNoCut away the background and build no base plate. Default: false.
removal_thresholdNoDepth below which the background is cut, 0.01-1. Used with remove_base. Default: 0.01.
base_thickness_mmNoBase plate thickness, 0.1-10 mm. Leave unset with remove_base.
bend_modeNooff, convex or concave. Default: off.
bend_axisNoxz curls the left and right edges; yz the top and bottom. Default: xz.
bend_angleNoArc of the bend in degrees, 0-360. Default: 60.
mesh_resolutionNoMesh points along the longer side, 512-2048. Default: 1024.

How to Use

  1. Upload the photo you want to turn into a relief.
  2. Choose emboss or engrave, the size and the carving depth.
  3. Optionally cut away the background or bend the plate.
  4. Submit the request and download the GLB, STL and depth map.

Pricing

OutputPrice per request
Relief (model and depth map, or depth map only)$0.80

Notes

  • The outputs are the GLB (no texture, in meters), the STL (millimeters, Z up) and the 16-bit grayscale depth map. A depth-map-only request returns only the depth map.
  • Higher mesh_resolution makes much larger files: about 40-50 MB GLB and 80-105 MB STL at 1024, and about 150 MB and 300 MB at 2048. A bend can push the STL much higher.
  • With remove_base on, a carving depth of 0 gives an empty model that still succeeds and is charged.
Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Relief API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/meshy/relief with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Relief below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "variant": "low",
    "should_generate_model": true,
    "size_mm": 60,
    "carving_mode": "emboss",
    "remove_base": false,
    "removal_threshold": 0.01,
    "bend_mode": "off",
    "bend_axis": "xz",
    "bend_angle": 60,
    "mesh_resolution": 1024
}
JSON
)

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

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

# 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' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/meshy/relief";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "variant": "low",
        "should_generate_model": true,
        "size_mm": 60,
        "carving_mode": "emboss",
        "remove_base": false,
        "removal_threshold": 0.01,
        "bend_mode": "off",
        "bend_axis": "xz",
        "bend_angle": 60,
        "mesh_resolution": 1024
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "variant": "low",
    "should_generate_model": True,
    "size_mm": 60,
    "carving_mode": "emboss",
    "remove_base": False,
    "removal_threshold": 0.01,
    "bend_mode": "off",
    "bend_axis": "xz",
    "bend_angle": 60,
    "mesh_resolution": 1024
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/meshy/relief", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

Relief API — Frequently asked questions

What is the Relief API?

Relief is a Meshy model for 3D asset generation from images, exposed as a REST API on WaveSpeedAI. Meshy Relief converts photos into embossed or engraved 3D reliefs, making it suitable for decorative models, plaques, medallions, 3D printing, and design workflows, with support for standard 3D and depth-map outputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Relief API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/meshy/meshy-relief.

How much does Relief cost per run or per second?

Relief starts at $0.8 per run or per second. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Relief accept?

Key inputs: `image`, `base_thickness_mm`, `bend_angle`, `bend_axis`, `bend_mode`, `carving_depth_mm`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/meshy/meshy-relief.

How long does Relief take to generate?

Reported generation time on WaveSpeedAI is around 65 seconds per request. This is an estimate, not a latency guarantee; queue time and input settings can change the total wait. live status is visible in the prediction record.

Can I use Relief outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Meshy). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.

llms.txt — meshy/relief for AI agents and LLMs