Transform your photos into ultra-high-resolution 3D models in seconds with Tencent's Hunyuan3D V3 Image to 3D. Film-quality geometry with PBR textures from single or multi-view images, ready for games, e-commerce, and 3D printing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
En attente
$0.25par exécution·~40 / $10



Hunyuan3D v3 Image-to-3D converts one (or several) reference images into a downloadable 3D asset—useful for product mockups, game props, e-commerce previews, and fast 3D prototyping.
You provide a primary image, optionally add side/back views for better reconstruction, and choose whether you want a fully textured model, a low-poly version, or geometry-only output.
Single-image 3D reconstruction
Generate a 3D model from one reference image via input_image_url.
Optional multi-view input for higher fidelity
Add back_image_url, left_image_url, and/or right_image_url to help the model recover shape details and reduce ambiguity.
Multiple generation modes (textured / low-poly / geometry-only)
Choose generate_type for a standard textured model, a low-poly reduction pass, or a “white model” without textures.
PBR material generation (when supported by mode)
Enable PBR textures using enable_pbr (note: it does not apply when generate_type is Geometry).
Mesh complexity controls
Target a face budget with face_count (range 40,000–1,500,000; default 500,000).
Low-poly topology options
When using generate_type: "LowPoly", choose polygon_type (triangles or quads).
Export-ready outputs Returns a GLB plus model URLs for additional formats (availability may vary by deployment).
Parameters
generate_type is Geometry).Normal, LowPoly, Geometry; default Normal).triangle or quadrilateral; default triangle).This endpoint is image-driven (no prompt parameter). For best results, put the “instructions” into the image selection:
input_image_url)back_image_url, left_image_url, right_image_url)Practical tips:
generate_type Choose what kind of 3D output you need:
Normal (default): Textured model
LowPoly: Polygon reduction workflow
Geometry: Geometry-only (no texture)
enable_pbr
true to request PBR materials
Note: ignored when generate_type is Geometry ([fal.ai][1])
face_count Controls mesh complexity. Higher values usually increase file size and can increase generation time.
Range: 40,000–1,500,000
Default: 500,000
polygon_type (only applies when generate_type is LowPoly)
triangle (default): best compatibility with real-time engines
quadrilateral: useful for some DCC workflows and retopo-friendly meshes
After you finish configuring the parameters, click Run, preview the result, and iterate if needed.
Per-run pricing varies by generate_type and optional features. Example pricing below is based on published unit prices for this model family.
| Typical settings | Estimated cost per run |
|---|---|
generate_type: Normal (default settings) | $0.375 |
generate_type: Normal + enable_pbr: true | $0.525 |
generate_type: Normal + enable_pbr: true + multi-view images | $0.675 |
generate_type: LowPoly (default polygon type) | $0.45 |
generate_type: Geometry | $0.225 |
left_image_url or back_image_url).Geometry when you only need a fast shape/mesh and plan to texture elsewhere—PBR settings won’t apply in this mode.face_count, then increase only if you need extra silhouette detail (and can afford larger files).Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan3d-v3/image-to-3d with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Hunyuan3d v3 Image To 3d below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"enable_pbr": false,
"polygon_type": "triangle",
"face_count": 500000,
"generate_type": "Normal"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan3d-v3/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
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan3d-v3/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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"enable_pbr": false,
"polygon_type": "triangle",
"face_count": 500000,
"generate_type": "Normal"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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));
}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",
"enable_pbr": False,
"polygon_type": "triangle",
"face_count": 500000,
"generate_type": "Normal"
}
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/wavespeed-ai/hunyuan3d-v3/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)Hunyuan3d v3 Image To 3d is a WaveSpeedAI model for 3D asset generation from images, exposed as a REST API on WaveSpeedAI. Transform your photos into ultra-high-resolution 3D models in seconds with Tencent's Hunyuan3D V3 Image to 3D. Film-quality geometry with PBR textures from single or multi-view images, ready for games, e-commerce, and 3D printing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
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/wavespeed-ai/hunyuan3d-v3-image-to-3d.
Hunyuan3d v3 Image To 3d starts at $0.25 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.
Key inputs: `image`, `back_image`, `enable_pbr`, `face_count`, `generate_type`, `left_image`. 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/wavespeed-ai/hunyuan3d-v3-image-to-3d.
Median end-to-end generation time on WaveSpeedAI is around 193 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.