> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.empiriolabs.ai/models/hitem3d-2-0/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server. # Hitem3D 2.0 > Production-focused image-to-3D with structure-aware textures, 1536 and 1536 Pro precision tiers, meshes up to two million faces, and five export formats. ![Hitem3D 2.0](https://media.empiriolabs.ai/model-logos/hitem3d-2-0.png) [Hitem3D](/providers/hitem3d) · 3D Generation `POST /v1/3d/generations` Production-focused image-to-3D with structure-aware textures, 1536 and 1536 Pro precision tiers, meshes up to two million faces, and five export formats. ## At a glance | Field | Value | | ------------------- | ----------------------------------------------------------- | | Model id | `hitem3d-2-0` | | Model release date | - | | Input modalities | Image | | Output modalities | 3D | | Context window | - | | Weight precision | - | | Region | Malaysia | | Features | image\_to\_3d, multi\_view, high\_poly, texture\_generation | | Native inference | No | | New | No | | Supported endpoints | `POST /v1/3d/generations` | | Alternate model ids | `hitem3d-2.0`, `hitem3d-2-0-251223` | ## Pricing | Charge | Spec | Rate | | -------------------- | ----------- | ------ | | 1536 textured | per request | \$2.80 | | 1536 Pro textured | per request | \$3.60 | | 1536 white model | per request | \$1.60 | | 1536 Pro white model | per request | \$2.40 | ## Example request ```bash curl https://api.empiriolabs.ai/v1/3d/generations \ -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \ -H 'Content-Type: application/json' \ -d '{"model": "hitem3d-2-0", "image_url": "https://example.com/product-photo.png", "resolution": "1024", "texture_size": "2048"}' ``` ## Parameters | Parameter | Type | Required | Default | Description | | ------------------ | ------- | -------- | -------- | --------------------------------------------------------------------------------------------------------------------------------- | | `image` | image | yes | - | One to four input images of the object. With multiple views, use multi\_images\_bit to declare the view order. | | `prompt` | string | no | - | Optional guidance text for the generation. | | `resolution` | enum | no | `"1536"` | Geometry resolution. 1536pro is the high-precision tier and bills at a higher per-generation rate. · Allowed: `1536`, `1536pro` | | `texture` | boolean | no | true | Generate textures with the geometry. Off returns a white model at a lower per-generation rate. | | `face_count` | integer | no | - | Target polygon count of the output mesh. · Range: 100000 – 2000000 | | `file_format` | enum | no | `"glb"` | 3D file format of the generated model. · Allowed: `glb`, `obj`, `stl`, `fbx`, `usdz` | | `multi_images_bit` | string | no | - | Four 0/1 digits declaring which views the input images are, in front, back, left, right order. Example: 1010 for front plus left. | ## Notes Image-to-3D only: one to four views of the object (declare the view order with multi\_images\_bit in front, back, left, right order). Billing is per generated model at the tier for the chosen resolution and texture setting. **Controls** * 1536 standard or 1536 Pro high-precision geometry. * texture on generates geometry and textures together in one pass; off returns a white model at a lower rate. * Target face count from 100,000 to 2,000,000, and glb, obj, stl, fbx, or usdz output. **Input limits** * Images: jpg, jpeg, png, or webp, under 4096x4096 px and 10 MB each, provided as URLs. **Output** * The generated file is stored and returned as a signed download URL. --- *Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/hitem3d-2-0`. > Production-focused image-to-3D with structure-aware textures, 1536 and 1536 Pro precision tiers, meshes up to two million faces, and five export formats.