# Rodin Gen-2 by Hyper3D

> Generate a clean, quad-topology 3D model with PBR textures (GLB, OBJ, USDZ, FBX, STL) from a text prompt or up to five reference images.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/hyper3d/rodin/gen-2`
- **Model ID**: `hyper3d/rodin/gen-2`
- **Category**: image-to-3d
- **Kind**: inference
- **Tags**: 3d, image-to-3d, text-to-3d, 3d-model-generator, mesh, quad-topology, pbr, hyper3d, rodin

## Pricing

- **Price**: $0.399 per output

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/hyper3d/rodin/gen-2` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/hyper3d/rodin/gen-2/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/hyper3d/rodin/gen-2/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/hyper3d/rodin/gen-2/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`seed`** (`integer | null`, _optional_):
  Random seed for reproducible generation. Leave unset for a random result.

- **`TAPose`** (`boolean`, _optional_):
  Generate human-like models in a rig-friendly T/A pose.
  - Default: `false`

- **`prompt`** (`string`, _optional_):
  Text description of the 3D object to generate (English only, up to 400 characters; longer text is truncated). Required for text-to-3D; provide this OR one or more input images.
  - Default: `""`

- **`material`** (`MaterialEnum`, _optional_):
  Material set baked into the mesh: PBR (physically based, default), Shaded, All, or None.
  - Default: `"PBR"`
  - Options: `"PBR"`, `"Shaded"`, `"All"`, `"None"`

- **`mesh_mode`** (`MeshModeEnum`, _optional_):
  Topology mode: Quad (default) for clean, animation-friendly quad topology, or Raw for a dense triangle mesh.
  - Default: `"Quad"`
  - Options: `"Raw"`, `"Quad"`

- **`hd_texture`** (`boolean`, _optional_):
  Generate high-definition texture maps for finer surface detail.
  - Default: `false`

- **`input_image_urls`** (`array<string>`, _optional_):
  One to five reference image URLs to reconstruct into a 3D model. Required for image-to-3D; provide these OR a text prompt.

- **`quality_override`** (`integer`, _optional_):
  Target face count. Leave unset to use the mode default (about 18k for Quad, 500k for Raw). Valid range depends on mesh_mode: Raw 500 to 1,000,000, Quad 1,000 to 200,000.
  - Range: `500` to `1000000`

- **`subdivisionlevel`** (`SubdivisionLevelEnum`, _optional_):
  Surface subdivision detail: high, medium (default), or low.
  - Default: `"medium"`
  - Options: `"high"`, `"medium"`, `"low"`

- **`geometry_file_format`** (`GeometryFileFormatEnum`, _optional_):
  Export format of the generated 3D mesh.
  - Default: `"glb"`
  - Options: `"glb"`, `"obj"`, `"usdz"`, `"fbx"`, `"stl"`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "TAPose": false,
  "prompt": "a bronze owl figurine with folded wings and layered feather detail",
  "material": "PBR",
  "mesh_mode": "Quad",
  "hd_texture": true,
  "input_image_urls": [
    "https://media.modelrunner.ai/652whXAMSt8ohZxvWYLAR.png"
  ],
  "subdivisionlevel": "medium",
  "geometry_file_format": "glb"
}
```

**Output**

```json
"https://media.modelrunner.ai/NGgwOkMwkQGFsCOFVOFrB.glb"
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/hyper3d/rodin/gen-2 \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "TAPose": false,
  "prompt": "a bronze owl figurine with folded wings and layered feather detail",
  "material": "PBR",
  "mesh_mode": "Quad",
  "hd_texture": true,
  "input_image_urls": [
    "https://media.modelrunner.ai/652whXAMSt8ohZxvWYLAR.png"
  ],
  "subdivisionlevel": "medium",
  "geometry_file_format": "glb"
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("hyper3d/rodin/gen-2", {
  input: {
  "TAPose": false,
  "prompt": "a bronze owl figurine with folded wings and layered feather detail",
  "material": "PBR",
  "mesh_mode": "Quad",
  "hd_texture": true,
  "input_image_urls": [
    "https://media.modelrunner.ai/652whXAMSt8ohZxvWYLAR.png"
  ],
  "subdivisionlevel": "medium",
  "geometry_file_format": "glb"
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "hyper3d/rodin/gen-2",
        arguments={
  "TAPose": false,
  "prompt": "a bronze owl figurine with folded wings and layered feather detail",
  "material": "PBR",
  "mesh_mode": "Quad",
  "hd_texture": true,
  "input_image_urls": [
    "https://media.modelrunner.ai/652whXAMSt8ohZxvWYLAR.png"
  ],
  "subdivisionlevel": "medium",
  "geometry_file_format": "glb"
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/hyper3d/rodin/gen-2)
- [OpenAPI Schema](https://modelrunner.ai/models/hyper3d/rodin/gen-2/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/hyper3d/rodin/gen-2/llms.txt)
- [Paper](https://arxiv.org/abs/2507.21493)