Seedream 5.0 Pro is LIVE | Try in Image Generator →

TripoSplat Image to 3D Gaussian Splat API

tripo3d /

TripoSplat is a fast AI image-to-3D Gaussian splat generation model that converts a single image into a high-quality 3D Gaussian splat file with PLY and SPLAT export options. Ready-to-use REST inference API for 3D reconstruction, Gaussian-splat workflows, product visualization, AR/VR content, game assets, digital twins, and professional 3D asset generation with simple integration, no coldstarts, and affordable pricing.

image-to-3d
Input

ExamplesView all

Related Models

README

Tripo3D TripoSplat Image-to-3D

Tripo3D TripoSplat Image-to-3D converts a single input image into a 3D Gaussian splat, suitable for fast view synthesis, lightweight 3D previews, and splat-based rendering workflows. It supports adjustable Gaussian count, inference steps, guidance strength, and export format selection.

Why Choose This?

  • Single-image 3D splat generation
    Turn one image into a 3D Gaussian splat without requiring multi-view capture.

  • Adjustable splat density
    Control num_gaussians to balance detail and file size.

  • Tunable generation quality
    Use num_inference_steps and guidance_scale to control fidelity and adherence to the source image.

  • Flexible export formats
    Export as ply or splat depending on your downstream workflow.

  • Production-ready API
    Useful for 3D previews, splat rendering, rapid prototyping, and lightweight scene reconstruction workflows.

Parameters

ParameterRequiredDescription
imageYesInput image to convert into a 3D Gaussian splat.
num_gaussiansNoTarget number of Gaussians in the output splat. Higher values can preserve more detail but create larger files. Range: 32768–262144. Default: 262144.
num_inference_stepsNoNumber of flow-matching sampler steps. More steps can improve fidelity with higher runtime. Range: 1–50. Default: 20.
guidance_scaleNoClassifier-free guidance strength. Higher values follow the input image more strongly but may oversaturate colors. Range: 0–10. Default: 3.
output_formatNoOutput Gaussian splat file format. Supported values: ply, splat. Default: ply.

How to Use

  1. Upload your image — provide the source image you want to convert.
  2. Set Gaussian count (optional) — choose how dense the splat should be.
  3. Adjust inference settings (optional) — tune num_inference_steps and guidance_scale as needed.
  4. Choose output format — select ply or splat.
  5. Submit — run the model and download the generated 3D splat file.

Example Use Case

Convert a product image into a 3D Gaussian splat for quick preview and interactive rendering.

Pricing

Just $0.05 per generation.

Billing Rules

  • Each generation costs $0.05
  • Pricing is fixed per request
  • num_gaussians, num_inference_steps, guidance_scale, and output_format do not affect pricing

Best Use Cases

  • 3D preview generation — Quickly turn still images into splat-based 3D assets.
  • Product visualization — Create lightweight 3D previews from catalog or product photos.
  • Rapid prototyping — Test 3D reconstruction ideas from a single source image.
  • Splat rendering workflows — Generate assets for tools or viewers that support Gaussian splats.
  • Creative experimentation — Explore image-to-3D conversion without complex capture setups.

Pro Tips

  • Use a clear, well-lit source image for better reconstruction quality.
  • Lower num_gaussians for smaller files and faster downstream handling.
  • Increase num_inference_steps when you want more fidelity and can tolerate longer runtime.
  • Adjust guidance_scale carefully if the output starts to look oversaturated or too tightly constrained.
  • Choose the output format that best matches your viewer or downstream toolchain.

Notes

  • image is required.
  • num_gaussians defaults to 262144.
  • num_inference_steps defaults to 20.
  • guidance_scale defaults to 3.
  • output_format defaults to ply.
  • Pricing is fixed at $0.05 per request.

Related Models

Note:This website uses AI models provided by third parties.

Triposplat Image To 3d API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/tripo3d/triposplat/image-to-3d 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 Triposplat Image To 3d 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",
    "num_gaussians": 262144,
    "num_inference_steps": 20,
    "guidance_scale": 3,
    "output_format": "ply"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/tripo3d/triposplat/image-to-3d" \
  -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=$(printf '%s' "$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' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/tripo3d/triposplat/image-to-3d";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "num_gaussians": 262144,
        "num_inference_steps": 20,
        "guidance_scale": 3,
        "output_format": "ply"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  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",
    "num_gaussians": 262144,
    "num_inference_steps": 20,
    "guidance_scale": 3,
    "output_format": "ply"
}

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/tripo3d/triposplat/image-to-3d", 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 = task.get("urls", {}).get("get") or 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"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Triposplat Image To 3d API — Frequently asked questions

What is the Triposplat Image To 3d API?

Triposplat Image To 3d is a Tripo3D model for 3D asset generation from images, exposed as a REST API on WaveSpeedAI. TripoSplat is a fast AI image-to-3D Gaussian splat generation model that converts a single image into a high-quality 3D Gaussian splat file with PLY and SPLAT export options. Ready-to-use REST inference API for 3D reconstruction, Gaussian-splat workflows, product visualization, AR/VR content, game assets, digital twins, and professional 3D asset generation with simple integration, no coldstarts, and affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Triposplat Image To 3d 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 production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/tripo3d/tripo3d-triposplat-image-to-3d.

How much does Triposplat Image To 3d cost per run?

Triposplat Image To 3d starts at $0.050 per run. 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 Triposplat Image To 3d accept?

Key inputs: `image`, `guidance_scale`, `num_inference_steps`, `num_gaussians`, `output_format`. 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/tripo3d/tripo3d-triposplat-image-to-3d.

How long does Triposplat Image To 3d take to generate?

Median end-to-end generation time on WaveSpeedAI is around 22 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Triposplat Image To 3d outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Tripo3D). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

TripoSplat Image to 3D Gaussian Splat API | WaveSpeedAI