TripoSplat Image to 3D Gaussian Splat API

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

Parameter	Required	Description
image	Yes	Input image to convert into a 3D Gaussian splat.
num_gaussians	No	Target number of Gaussians in the output splat. Higher values can preserve more detail but create larger files. Range: `32768–262144`. Default: `262144`.
num_inference_steps	No	Number of flow-matching sampler steps. More steps can improve fidelity with higher runtime. Range: `1–50`. Default: `20`.
guidance_scale	No	Classifier-free guidance strength. Higher values follow the input image more strongly but may oversaturate colors. Range: `0–10`. Default: `3`.
output_format	No	Output Gaussian splat file format. Supported values: `ply`, `splat`. Default: `ply`.

How to Use

Upload your image — provide the source image you want to convert.
Set Gaussian count (optional) — choose how dense the splat should be.
Adjust inference settings (optional) — tune num_inference_steps and guidance_scale as needed.
Choose output format — select ply or splat.
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

Tripo3D H3.1 Image-to-3D — Generate a more traditional textured 3D model from a single image.
Tripo3D H3.1 Multiview-to-3D — Use multiple reference images for higher-accuracy 3D reconstruction.

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; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Triposplat Image To 3d below.

HTTP example

# Submit the prediction
curl -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 '{
    "image": "https://example.com/your-input.jpg",
    "num_gaussians": 262144,
    "num_inference_steps": 20,
    "guidance_scale": 3,
    "output_format": "ply"
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("tripo3d/triposplat/image-to-3d", {
        "image": "https://example.com/your-input.jpg",
        "num_gaussians": 262144,
        "num_inference_steps": 20,
        "guidance_scale": 3,
        "output_format": "ply"
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "tripo3d/triposplat/image-to-3d",
    {
    "image": "https://example.com/your-input.jpg",
    "num_gaussians": 262144,
    "num_inference_steps": 20,
    "guidance_scale": 3,
    "output_format": "ply"
}
)

print(output["outputs"][0])  # → URL of the generated output

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 prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. 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 do I get started with the Triposplat Image To 3d API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

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.

示例查看全部

相关模型

README