---
title: TRELLIS.2 | Runware Docs
url: https://runware.ai/docs/models/microsoft-trellis-2
description: High-fidelity image-to-3D generative model with compact structured latents
---
# TRELLIS.2

TRELLIS.2 is a 4-billion-parameter 3D generative model that transforms 2D images into fully textured 3D assets with complex topology, sharp features, and physically based rendering materials. It uses a novel field-free sparse voxel representation and scalable structured latent space to enable efficient, high-resolution 3D generation from single image input.

- **ID**: `microsoft:trellis-2@4b`
- **Status**: live
- **Creator**: Microsoft
- **Release Date**: December 17, 2025
- **Capabilities**: Image to 3D

## Pricing

Pricing is based on processing time. Most generations cost just a few cents, depending on complexity.

- **1024x1024**: `$0.0256`

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/microsoft-trellis-2#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `3dInference`

Identifier for the type of task being performed

### [taskUUID](https://runware.ai/docs/models/microsoft-trellis-2#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/microsoft-trellis-2#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

3D output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/microsoft-trellis-2#request-outputformat)

- **Type**: `string`
- **Default**: `GLB`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

**Allowed values**: `GLB`

### [webhookURL](https://runware.ai/docs/models/microsoft-trellis-2#request-webhookurl)

- **Type**: `string`
- **Format**: `URI`

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/platform/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/microsoft-trellis-2#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns complete results directly in the API response.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/platform/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/microsoft-trellis-2#request-uploadendpoint)

- **Type**: `string`
- **Format**: `URI`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [ttl](https://runware.ai/docs/models/microsoft-trellis-2#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/microsoft-trellis-2#request-includecost)

- **Type**: `boolean`
- **Default**: `false`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/microsoft-trellis-2#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [image](https://runware.ai/docs/models/microsoft-trellis-2#request-inputs-image)

- **Path**: `inputs.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

**Generation Parameters**

Core parameters for controlling the generated content.

### [model](https://runware.ai/docs/models/microsoft-trellis-2#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `microsoft:trellis-2@4b`

Identifier of the model to use for generation.

**Learn more** (3 resources):

- [Text To Image: Model Selection The Foundation Of Generation](https://runware.ai/docs/guides/text-to-image#model-selection-the-foundation-of-generation) (guide)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/guides/image-inpainting#model-specialized-inpainting-models) (guide)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/guides/image-outpainting#other-critical-parameters) (guide)

### [seed](https://runware.ai/docs/models/microsoft-trellis-2#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `9223372036854776000`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

**Learn more** (1 resource):

- [Text To Image: Seed Controlling Randomness Deterministically](https://runware.ai/docs/guides/text-to-image#seed-controlling-randomness-deterministically) (guide)

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [resolution](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-resolution)

- **Path**: `settings.resolution`
- **Type**: `integer`
- **Default**: `1024`

Voxel grid resolution for 3D generation. Higher values capture finer geometric detail.

**Allowed values**: `512` `1024` `1536`

### [decimationTarget](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-decimationtarget)

- **Path**: `settings.decimationTarget`
- **Type**: `integer`
- **Min**: `100000`
- **Max**: `1000000`
- **Default**: `500000`

Target polygon count for mesh simplification. Lower values produce lighter models at the cost of geometric detail.

### [remesh](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-remesh)

- **Path**: `settings.remesh`
- **Type**: `boolean`
- **Default**: `true`

Whether to remesh the output for cleaner topology.

### [shapeSlat](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-shapeslat)

- **Path**: `settings.shapeSlat`
- **Type**: `object (4 properties)`

Sampler for the Structured Latent stage that refines the 3D geometry.

#### [steps](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-shapeslat-steps)

- **Path**: `settings.shapeSlat.steps`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `50`

Number of denoising steps. More steps improve quality but increase generation time.

#### [guidanceRescale](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-shapeslat-guidancerescale)

- **Path**: `settings.shapeSlat.guidanceRescale`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`

Dampens oversaturation from high guidance values. Lower values apply more correction.

#### [guidanceStrength](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-shapeslat-guidancestrength)

- **Path**: `settings.shapeSlat.guidanceStrength`
- **Type**: `float`
- **Min**: `1`
- **Max**: `10`

How closely the output follows the input image. Higher values enforce stricter adherence to the visible geometry.

#### [rescaleT](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-shapeslat-rescalet)

- **Path**: `settings.shapeSlat.rescaleT`
- **Type**: `float`
- **Min**: `1`
- **Max**: `6`

Timestep rescaling factor for the sampling schedule. Controls how guidance strength is distributed across steps.

### [sparseStructure](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-sparsestructure)

- **Path**: `settings.sparseStructure`
- **Type**: `object (4 properties)`

Sampler for the initial sparse voxel grid that establishes the basic 3D geometry.

#### [steps](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-sparsestructure-steps)

- **Path**: `settings.sparseStructure.steps`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `50`

Number of denoising steps. More steps improve quality but increase generation time.

#### [guidanceRescale](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-sparsestructure-guidancerescale)

- **Path**: `settings.sparseStructure.guidanceRescale`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`

Dampens oversaturation from high guidance values. Lower values apply more correction.

#### [guidanceStrength](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-sparsestructure-guidancestrength)

- **Path**: `settings.sparseStructure.guidanceStrength`
- **Type**: `float`
- **Min**: `1`
- **Max**: `10`

How closely the output follows the input image. Higher values enforce stricter adherence to the visible geometry.

#### [rescaleT](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-sparsestructure-rescalet)

- **Path**: `settings.sparseStructure.rescaleT`
- **Type**: `float`
- **Min**: `1`
- **Max**: `6`

Timestep rescaling factor for the sampling schedule. Controls how guidance strength is distributed across steps.

### [texSlat](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-texslat)

- **Path**: `settings.texSlat`
- **Type**: `object (4 properties)`

Sampler for the Structured Latent stage that generates surface appearance.

#### [steps](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-texslat-steps)

- **Path**: `settings.texSlat.steps`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `50`

Number of denoising steps. More steps improve quality but increase generation time.

#### [guidanceRescale](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-texslat-guidancerescale)

- **Path**: `settings.texSlat.guidanceRescale`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`

Dampens oversaturation from high guidance values. Lower values apply more correction.

#### [guidanceStrength](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-texslat-guidancestrength)

- **Path**: `settings.texSlat.guidanceStrength`
- **Type**: `float`
- **Min**: `1`
- **Max**: `10`

How closely the output follows the input image. Higher values enforce stricter adherence to the visible geometry.

#### [rescaleT](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-texslat-rescalet)

- **Path**: `settings.texSlat.rescaleT`
- **Type**: `float`
- **Min**: `1`
- **Max**: `6`

Timestep rescaling factor for the sampling schedule. Controls how guidance strength is distributed across steps.

### [textureSize](https://runware.ai/docs/models/microsoft-trellis-2#request-settings-texturesize)

- **Path**: `settings.textureSize`
- **Type**: `integer`
- **Min**: `1024`
- **Max**: `4096`
- **Step**: `1024`
- **Default**: `2048`

Resolution of the output texture map in pixels. Higher values produce finer surface detail.

## Response Parameters

### [taskType](https://runware.ai/docs/models/microsoft-trellis-2#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `3dInference`

Type of the task.

### [taskUUID](https://runware.ai/docs/models/microsoft-trellis-2#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the task.

### [seed](https://runware.ai/docs/models/microsoft-trellis-2#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [cost](https://runware.ai/docs/models/microsoft-trellis-2#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

### [modelUUID](https://runware.ai/docs/models/microsoft-trellis-2#response-modeluuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output 3D model file.

### [modelURL](https://runware.ai/docs/models/microsoft-trellis-2#response-modelurl)

- **Type**: `string`
- **Format**: `URI`

URL of the output 3D model file.

### [modelBase64Data](https://runware.ai/docs/models/microsoft-trellis-2#response-modelbase64data)

- **Type**: `string`

Base64-encoded 3D model file data.

### [modelDataURI](https://runware.ai/docs/models/microsoft-trellis-2#response-modeldatauri)

- **Type**: `string`
- **Format**: `URI`

Data URI of the output 3D model file.

## Examples

### Orc Character Bust (Image to 3D)

[View 3D model](https://assets.runware.ai/examples/microsoft-trellis-2/8065edb8-6803-41ce-bc6b-4bff587fc43e.glb)

**Request**:

```json
{
  "taskType": "3dInference",
  "taskUUID": "bd373968-8512-4315-a95f-95a4401fea3e",
  "model": "microsoft:trellis-2@4b",
  "seed": 424242,
  "settings": {
    "textureSize": 2048,
    "decimationTarget": 500000,
    "remesh": true,
    "resolution": 1024,
    "sparseStructure": {
      "guidanceStrength": 8,
      "guidanceRescale": 0.7,
      "steps": 30,
      "rescaleT": 3
    },
    "shapeSlat": {
      "guidanceStrength": 7.5,
      "guidanceRescale": 0.7,
      "steps": 28,
      "rescaleT": 3
    },
    "texSlat": {
      "guidanceStrength": 8.5,
      "guidanceRescale": 0.6,
      "steps": 30,
      "rescaleT": 3
    }
  },
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/41d320a9-1ed2-4dd8-9727-d83297535d02.jpg"
  }
}
```

**Response**:

```json
{
  "taskType": "3dInference",
  "taskUUID": "bd373968-8512-4315-a95f-95a4401fea3e",
  "seed": 424242,
  "cost": 0.055,
  "outputs": {
    "files": [
      {
        "uuid": "112a24e5-7976-46b3-a22c-e658daaffdfe",
        "url": "https://im.runware.ai/image/os/a01d21/ws/4/ii/112a24e5-7976-46b3-a22c-e658daaffdfe.glb"
      }
    ]
  }
}
```

---

### Ornate Dragon Figurine (Image to 3D)

[View 3D model](https://assets.runware.ai/examples/microsoft-trellis-2/2f356285-8402-4afa-b8b9-2664dc0a4d67.glb)

**Request**:

```json
{
  "taskType": "3dInference",
  "taskUUID": "5efab433-316e-4b0b-b8c4-6e0edbe3779c",
  "model": "microsoft:trellis-2@4b",
  "seed": 246813579,
  "settings": {
    "textureSize": 4096,
    "decimationTarget": 500000,
    "remesh": true,
    "resolution": 1536,
    "sparseStructure": {
      "guidanceStrength": 8,
      "guidanceRescale": 0.7,
      "steps": 30,
      "rescaleT": 3
    },
    "shapeSlat": {
      "guidanceStrength": 7.5,
      "guidanceRescale": 0.7,
      "steps": 28,
      "rescaleT": 3
    },
    "texSlat": {
      "guidanceStrength": 8.5,
      "guidanceRescale": 0.6,
      "steps": 32,
      "rescaleT": 3
    }
  },
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/59b5b9e2-7083-4adf-88be-2793dab06233.jpg"
  }
}
```

**Response**:

```json
{
  "taskType": "3dInference",
  "taskUUID": "5efab433-316e-4b0b-b8c4-6e0edbe3779c",
  "seed": 246813579,
  "cost": 0.0198,
  "outputs": {
    "files": [
      {
        "uuid": "2dba7e00-adc6-410e-bcf9-7011266bf24f",
        "url": "https://im.runware.ai/image/os/a24d12/ws/4/ii/2dba7e00-adc6-410e-bcf9-7011266bf24f.glb"
      }
    ]
  }
}
```

---

### Ornate Fantasy Helmet (Image to 3D)

[View 3D model](https://assets.runware.ai/examples/microsoft-trellis-2/b1e1d161-708c-4508-8bfa-8e97b3bffb8e.glb)

**Request**:

```json
{
  "taskType": "3dInference",
  "taskUUID": "0ccf2b8e-db45-4439-bba8-6a1420848399",
  "model": "microsoft:trellis-2@4b",
  "seed": 424242,
  "settings": {
    "textureSize": 4096,
    "decimationTarget": 500000,
    "remesh": true,
    "resolution": 1536,
    "sparseStructure": {
      "guidanceStrength": 8,
      "guidanceRescale": 0.7,
      "steps": 30,
      "rescaleT": 3
    },
    "shapeSlat": {
      "guidanceStrength": 7.5,
      "guidanceRescale": 0.7,
      "steps": 28,
      "rescaleT": 3
    },
    "texSlat": {
      "guidanceStrength": 8.5,
      "guidanceRescale": 0.6,
      "steps": 32,
      "rescaleT": 3
    }
  },
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/84e77cec-bda0-4930-94f8-cacad245251d.jpg"
  }
}
```

**Response**:

```json
{
  "taskType": "3dInference",
  "taskUUID": "0ccf2b8e-db45-4439-bba8-6a1420848399",
  "seed": 424242,
  "cost": 0.0454,
  "outputs": {
    "files": [
      {
        "uuid": "7e34d8eb-0823-4d73-bde7-8599a08bb505",
        "url": "https://im.runware.ai/image/os/a05d22/ws/4/ii/7e34d8eb-0823-4d73-bde7-8599a08bb505.glb"
      }
    ]
  }
}
```

---

### Hero Product Figurine (Image to 3D)

[View 3D model](https://assets.runware.ai/examples/microsoft-trellis-2/a07acd5b-af83-44b3-a667-811cbdffce1b.glb)

**Request**:

```json
{
  "taskType": "3dInference",
  "taskUUID": "a8970b6f-a3d2-4fcd-abdb-6d44ac3477f0",
  "model": "microsoft:trellis-2@4b",
  "seed": 424242,
  "settings": {
    "textureSize": 4096,
    "decimationTarget": 500000,
    "remesh": true,
    "resolution": 1536,
    "sparseStructure": {
      "guidanceStrength": 8,
      "guidanceRescale": 0.7,
      "steps": 28,
      "rescaleT": 3
    },
    "shapeSlat": {
      "guidanceStrength": 7.5,
      "guidanceRescale": 0.7,
      "steps": 30,
      "rescaleT": 3
    },
    "texSlat": {
      "guidanceStrength": 8.5,
      "guidanceRescale": 0.6,
      "steps": 32,
      "rescaleT": 3
    }
  },
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/223fe72c-93a2-4a97-9c2a-81183a365353.jpg"
  }
}
```

**Response**:

```json
{
  "taskType": "3dInference",
  "taskUUID": "a8970b6f-a3d2-4fcd-abdb-6d44ac3477f0",
  "seed": 424242,
  "cost": 0.0314,
  "outputs": {
    "files": [
      {
        "uuid": "6568996e-9567-4a40-84b4-1cc6202fe043",
        "url": "https://im.runware.ai/image/os/a03d21/ws/4/ii/6568996e-9567-4a40-84b4-1cc6202fe043.glb"
      }
    ]
  }
}
```