Hyper3D Rodin V2.5 Image-to-3D API

hyper3d/rodin-v2.5/image-to-3d

Hyper3D Rodin v2.5 is a fast AI image-to-3D generation model that turns reference images into production-ready 3D assets with clean meshes, UVs, and textures. Ready-to-use REST inference API for game assets, e-commerce 3D models, product visualization, AR/VR content, digital twins, creative design, and professional 3D asset generation workflows with simple integration, no coldstarts, and affordable pricing.

Image to 3D
Giriş

Sürükleyip bırakın veya yüklemek için tıklayın

preview

Boşta

3D

$0.48çalıştırma başına·~20 / $10

ÖrneklerTümünü görüntüle

3D
3D
3D
3D
3D

İlgili Modeller

README

Hyper3D Rodin Image-to-3D

Hyper3D Rodin Image-to-3D generates 3D assets from one or more reference images, with optional text guidance and flexible controls for mesh density, texture output, pose, and export format. It is suitable for product concepts, stylized objects, character prototyping, game assets, and other image-to-3D workflows where you want direct control over geometry and material output.

Why Choose This?

  • Image-guided 3D generation
    Turn one or more reference images into a 3D asset with minimal setup.

  • Flexible mesh and quality options
    Choose between quad and triangle outputs across multiple density levels.

  • Material and texture control
    Generate PBR, shaded, or full material sets depending on your workflow.

  • Multiple export formats
    Export as glb, obj, or stl.

  • Production-ready workflow
    Useful for concept art, product prototyping, game asset generation, and 3D content pipelines.

Parameters

ParameterRequiredDescription
imagesYesReference images for generating the 3D model. Upload 1–5 images.
promptNoOptional text prompt. If empty, the model auto-generates a prompt from the images.
use_original_alphaNoPreserve the transparency channel from input images. Default: false.
geometry_file_formatNoOutput geometry file format. Supported values: glb, obj, stl. Default: glb.
materialNoMaterial output type. Supported values: PBR, Shaded, All. Default: All.
quality_and_meshNoCombined quality and mesh type selection. Supported values: 4K Quad, 8K Quad, 18K Quad, 50K Quad, 2K Triangle, 20K Triangle, 150K Triangle, 500K Triangle. Default: 500K Triangle.
hd_textureNoEnable enhanced texture post-processing. Default: false.
ta_poseNoGenerate characters in T-pose or A-pose format. Default: false.
addonsNoOptional add-on. Supported value: HighPack. Enables 4K textures and higher-poly geometry.

How to Use

  1. Upload your reference images — provide 1–5 images of the object, character, or asset you want to generate.
  2. Add a prompt (optional) — describe the asset if you want to guide shape, style, or design intent more explicitly.
  3. Choose mesh and format settings — set quality_and_mesh, geometry_file_format, and material based on your downstream use.
  4. Adjust texture controls (optional) — fine-tune hd_texture and related settings.
  5. Add HighPack (optional) — enable addons = HighPack if you need higher-end texture and geometry output.
  6. Submit — run the model and download the generated 3D asset.

Example Use Case

Generate a clean 3D product model from multiple reference photos, with PBR materials and quad mesh output for downstream rendering or e-commerce visualization.

Pricing

Pricing is charged per generation.

ConfigurationCost
Standard$0.48
Standard + HighPack$1.44

Billing Rules

  • Base price is $0.48 per generation
  • HighPack adds an additional $0.96 per generation
  • Other parameters do not affect pricing

Best Use Cases

  • Product concept modeling — Build 3D product shapes from reference photos.
  • Game asset prototyping — Generate early 3D assets for props, items, and stylized objects.
  • Character base generation — Create starting meshes for stylized or realistic character workflows.
  • AR/VR content preparation — Build assets for immersive applications and previews.
  • Creative 3D ideation — Rapidly test multiple visual directions before manual refinement.

Pro Tips

  • Upload clean, well-lit reference images for better shape and texture consistency.
  • Use multiple views when structure accuracy matters.
  • Choose quad output when downstream retopology or sculpting workflows matter.
  • Add HighPack only when you need the extra texture and geometry quality, since it increases cost significantly.

Notes

  • images is required.
  • You can upload up to 5 reference images.
  • prompt is optional; if omitted, the model can infer guidance from the images.
  • HighPack adds an extra fixed charge on top of the base price.
  • geometry_file_format defaults to glb.
  • material defaults to All.
  • quality_and_mesh defaults to 500K Triangle.

Related Models

  • Hyper3D Rodin Text-to-3D — Generate 3D assets directly from text prompts.
  • Other Hyper3D Rodin workflows — Useful when you need different 3D generation paths or input modalities.
  • 3D asset generation pipelines — Useful when image-to-3D is only one part of a broader modeling workflow.
Not:Bu web sitesi, üçüncü taraflarca sağlanan yapay zeka modellerini kullanmaktadır. Belge fiyatları yalnızca referans amaçlıdır ve güncelliğini yitirebilir. Generate düğmesi bir tahmin gösterir; nihai görev ücreti geçerlidir.

Rodin v2.5 Image To 3d API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/hyper3d/rodin-v2.5/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 Rodin v2.5 Image To 3d below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "images": [
        "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
    ],
    "use_original_alpha": false,
    "geometry_file_format": "glb",
    "material": "All",
    "quality_and_mesh": "500K Triangle",
    "hd_texture": false,
    "ta_pose": false,
    "addons": "HighPack"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/hyper3d/rodin-v2.5/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="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/hyper3d/rodin-v2.5/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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "images": [
                "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
        ],
        "use_original_alpha": false,
        "geometry_file_format": "glb",
        "material": "All",
        "quality_and_mesh": "500K Triangle",
        "hd_texture": false,
        "ta_pose": false,
        "addons": "HighPack"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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 = {
    "images": [
        "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
    ],
    "use_original_alpha": False,
    "geometry_file_format": "glb",
    "material": "All",
    "quality_and_mesh": "500K Triangle",
    "hd_texture": False,
    "ta_pose": False,
    "addons": "HighPack"
}

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/hyper3d/rodin-v2.5/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 = 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)

Rodin v2.5 Image To 3d API — Frequently asked questions

What is the Rodin v2.5 Image To 3d API?

Rodin v2.5 Image To 3d is a Hyper3d model for 3D asset generation from images, exposed as a REST API on WaveSpeedAI. Hyper3D Rodin v2.5 is a fast AI image-to-3D generation model that turns reference images into production-ready 3D assets with clean meshes, UVs, and textures. Ready-to-use REST inference API for game assets, e-commerce 3D models, product visualization, AR/VR content, digital twins, creative design, and professional 3D asset generation workflows 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 Rodin v2.5 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 Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/hyper3d/rodin-v2.5/image-to-3d.

How much does Rodin v2.5 Image To 3d cost per run or per second?

Rodin v2.5 Image To 3d starts at $0.48 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 Rodin v2.5 Image To 3d accept?

Key inputs: `prompt`, `images`, `addons`, `geometry_file_format`, `hd_texture`, `material`. 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/hyper3d/rodin-v2.5/image-to-3d.

How long does Rodin v2.5 Image To 3d take to generate?

Reported generation time on WaveSpeedAI is around 126 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 Rodin v2.5 Image To 3d outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Hyper3d). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.

llms.txt — hyper3d/rodin-v2.5/image-to-3d for AI agents and LLMs