Hunyuan3d V3 Image To 3d

Hunyuan3d V3 Image To 3d

Playground

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.

Features

WaveSpeedAI Hunyuan3D v3 Image-to-3D

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.

Key capabilities

• 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 and how to use

Parameters

• input_image_url: (required) URL of the main image used to generate the 3D model.
• back_image_url: Optional back-view image URL for better reconstruction.
• left_image_url: Optional left-view image URL for better reconstruction.
• right_image_url: Optional right-view image URL for better reconstruction.
• enable_pbr: Whether to enable PBR material generation (ignored when generate_type is Geometry).
• face_count: Target face count (40,000–1,500,000; default 500,000).
• generate_type: Generation mode (Normal, LowPoly, Geometry; default Normal).
• polygon_type: Polygon type for low-poly output (triangle or quadrilateral; default triangle).

Prompt

This endpoint is image-driven (no prompt parameter). For best results, put the “instructions” into the image selection:

• Use a clear, well-lit image with the subject centered.
• Avoid heavy motion blur, extreme fisheye distortion, or cluttered backgrounds.
• If the subject has thin parts (straps, antennae, wires), add side/back views to reduce missing geometry.

Media (Images)

• Required: 1 image (input_image_url)
• Optional: up to 3 additional views (back_image_url, left_image_url, right_image_url)
• Common accepted formats in UI workflows: jpg, jpeg, png, webp, gif, avif

Practical tips:

• Use consistent framing across views (similar distance and scale).
• Keep the subject fully in frame—cropped objects tend to produce incomplete meshes.
• If you only have one view, pick the angle that best shows the overall silhouette.

Other parameters

• 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.

Pricing

Per-run pricing varies by generate_type and optional features. Example pricing below is based on published unit prices for this model family.

Notes

• If you’re seeing “melted” surfaces or missing parts, add at least one more view (left_image_url or back_image_url).
• Use Geometry when you only need a fast shape/mesh and plan to texture elsewhere—PBR settings won’t apply in this mode.
• Start with the default face_count, then increase only if you need extra silhouette detail (and can afford larger files).

Related Models

• Hunyuan3D V2 Multi-View – Multi-view-focused reconstruction when you can provide several angles.
• Hunyuan3D V2 Mini – Lighter-weight Hunyuan3D option for faster iteration.
• Tripo3D v2.5 Image-to-3D – Single-image 3D generation with a simple input surface.
• Hyper3D Rodin v2 Image-to-3D – Production-oriented image-to-3D workflow (UVs/textures-focused).

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan3d-v3/image-to-3d" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "enable_pbr": false,
    "polygon_type": "triangle",
    "face_count": 500000,
    "generate_type": "Normal"
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"