Hitem3d Hi3d V3.0 Image To 3d API Documentation

Hitem3d Hi3d V3.0 Image To 3d API Documentation

Playground

Try it on WaveSpeedAI!

Hi3D V3.0 Image-to-3D converts a single reference image into a detailed 3D mesh with optional textures, PBR materials, and multiple export formats for game assets, product visualization, 3D design, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Hi3D V3.0 Image to 3D converts one reference image into a detailed 3D mesh. It supports texture generation, PBR material maps, configurable face count, and multiple 3D export formats including GLB, OBJ, STL, FBX, and USDZ.


Why Choose This?

  • Single-image 3D generation
    Create a detailed 3D model from one reference image.

  • Quality and master modes
    Choose 2048quality for faster generation or 2048master for higher-quality output.

  • Texture and PBR support
    Generate textured 3D assets and optional PBR material maps for more production-ready results.

  • Configurable geometry
    Set a target face count for different quality, detail, or downstream workflow needs.

  • Multiple export formats
    Export generated models as glb, obj, stl, fbx, or usdz.

  • Shading control
    Adjust de-shading strength to improve texture and material consistency.


Parameters

ParameterRequiredDescription
imageYesInput PNG, JPEG, or WebP image. Maximum file size: 20 MB.
resolutionNoGeneration quality mode: 2048quality for faster generation or 2048master for the highest quality.
enable_textureNoGenerate textures in addition to geometry. Default: true.
enable_pbrNoGenerate PBR material maps with the texture. Default: true. Ignored when enable_texture is disabled.
face_countNoTarget face count for the generated mesh. Range: 100000–5000000.
export_formatNoOutput format: glb, obj, stl, fbx, or usdz.
shadingNoDe-shading strength. Range: 0–1. Default: 0.5.

How to Use

  1. Upload a reference image — Provide a clear PNG, JPEG, or WebP image of the target object.
  2. Choose resolution — Use 2048quality for faster generation or 2048master for higher-quality output.
  3. Configure texture optional — Keep enable_texture enabled when you need textured output.
  4. Configure PBR optional — Keep enable_pbr enabled when PBR material maps are needed.
  5. Set face count optional — Choose a target face count based on your geometry detail needs.
  6. Choose export format — Select glb, obj, stl, fbx, or usdz.
  7. Adjust shading optional — Use shading to control de-shading strength.
  8. Submit — Generate the 3D model and retrieve the output through the standard WaveSpeed prediction response.

Pricing

Pricing is based on selected resolution, texture generation, and PBR generation. Each run is billed once at the price below for the options you choose.

ResolutionGeometry only (no texture)Texture (no PBR)Texture + PBR
2048quality$2.16$2.40$2.52
2048master$10.56$10.80$10.92

With default settings (2048quality, texture and PBR enabled), one run costs $2.52 per run.

PBR is only generated and priced when texture generation is enabled.


Best Use Cases

  • Single-image 3D asset creation — Convert one reference image into a usable 3D model.
  • Product visualization — Generate 3D product assets for previews, demos, and interactive content.
  • Game and real-time workflows — Create geometry with configurable face count for downstream optimization.
  • E-commerce assets — Produce 3D models for online product display.
  • Design prototyping — Turn concept images into 3D assets for review and iteration.
  • Production-ready exports — Use GLB, OBJ, STL, FBX, or USDZ depending on your pipeline.

Pro Tips

  • Use a clear, well-lit image with the object fully visible.
  • Avoid heavy occlusion, cluttered backgrounds, strong reflections, or motion blur.
  • Use 2048quality for faster iteration and 2048master for higher-quality final assets.
  • Enable textures when color and surface detail matter.
  • Enable PBR when the model needs richer material response in downstream 3D tools.
  • Set face_count based on the target workflow: lower for real-time use, higher for detail preservation.
  • Use glb for general-purpose 3D workflows and usdz when USDZ output is required.


## Authentication

For authentication details, please refer to the [Authentication Guide](/api-authentication).

## API Endpoints

### Submit Task & Query Result

<ApiTabs submitUrl={model.submitUrl} resultUrl={model.resultUrl} payload={model.defaultValues} />

## Parameters

### Task Submission Parameters

#### Request Parameters

<RequestParams params={model.params} conditions={model.conditions} />

Every model also accepts the global request options [`enable_sync_mode`](/sync-mode) and [`enable_base64_output`](/base64-output); see their pages for details.

#### Response Parameters

<SubmitResponse />

#### Result Request Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| id | string | Yes | - | Task ID |

#### Result Response Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., "success") |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array&lt;string \| object&gt; | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Status: `completed` is successful; `failed`, `cancelled`, `timeout`, and `deleted` are failure terminal statuses |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
© 2026 WaveSpeedAI. All rights reserved.