---
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](https://assets.runware.ai/covers/microsoft-trellis-2.jpg)

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.

- **Status**: live
- **ID**: `microsoft:trellis-2@4b`
- Try in Playground
- **Creator**: Microsoft
- **Release Date**: December 17, 2025
- **Zero Data Retention**: Yes
- **Capabilities**: Image to 3D, Checkpoint

## Pricing

$0.0193 from, per run · ~32s per request

**Measured runs**

- settings.resolution 512 · 1024×1024 input: `$0.0193` (~16s)
- settings.textureSize 1024 · 1024×1024 input: `$0.0208` (~19s)
- 1024×1024 input: `$0.0298` (~24s)
- settings.texSlat.steps 40 · 1024×1024 input: `$0.0357` (~29s)
- settings.shapeSlat.steps 40 · 1024×1024 input: `$0.0432` (~34s)
- settings.sparseStructure.steps 40 · 1024×1024 input: `$0.0446` (~34s)
- settings.resolution 1536 · 1024×1024 input: `$0.0521` (~40s)
- settings.textureSize 4096 · 1024×1024 input: `$0.0595` (~45s)

**4 example generations**

- [image-to-3d](https://runware.ai/docs/models/microsoft-trellis-2/examples#example-portable-farrier-hoof-stand-model): `$0.009` (~21s)
- [image-to-3d](https://runware.ai/docs/models/microsoft-trellis-2/examples#example-underground-safety-mole-character-model): `$0.0166` (~30s)
- [image-to-3d](https://runware.ai/docs/models/microsoft-trellis-2/examples#example-neon-laundromat-cutaway-set-module): `$0.0218` (~1m 19s)
- [image-to-3d](https://runware.ai/docs/models/microsoft-trellis-2/examples#example-tidal-monitoring-cabin-environment-module): `$0.0269` (~46s)

billed by compute time, so a request costs what it took · times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

When `inputs.meshFile` is provided, `settings.shapeSlat`, `settings.sparseStructure`, `settings.decimationTarget`, `settings.remesh`, `settings.remeshBand`, `settings.remeshProject`, and `settings.meshCluster` cannot be used.

---

When `settings.dracoCompression.enabled` is not `true`, `settings.dracoCompression.level`, `settings.dracoCompression.quantizationNormal`, `settings.dracoCompression.quantizationPosition`, and `settings.dracoCompression.quantizationTexCoord` cannot be used.

## 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.

- \`GLB\`: Binary glTF format for 3D models, including geometry, textures, and PBR materials.

**Allowed values**: `GLB`

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

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses 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/models-api/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 results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/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`

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).

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

- **Path**: `inputs.meshFile`
- **Type**: `string`

3D model to re-texture (UUID or URL). Skips geometry generation and applies new textures using the reference image.

**Core Parameters**

Primary parameters that define the task output.

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

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

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [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):

- [Seed](https://runware.ai/docs/learn/seed) (learn)

**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`

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

- **Path**: `settings.alphaMode`
- **Type**: `string`
- **Default**: `OPAQUE`

Material alpha mode for the output mesh.

**Allowed values**: `OPAQUE` `BLEND` `MASK`

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

- **Path**: `settings.decimationTarget`
- **Type**: `integer`
- **Min**: `5000`
- **Max**: `1000000`
- **Default**: `500000`

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

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

- **Path**: `settings.dracoCompression`
- **Type**: `object (5 properties)`

Apply KHR\_draco\_mesh\_compression to the output GLB. Reduces geometry size 5-10x with no triangle loss.

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

- **Path**: `settings.dracoCompression.enabled`
- **Type**: `boolean`

Compress the output GLB geometry with Draco.

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

- **Path**: `settings.dracoCompression.level`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `10`
- **Default**: `7`

Encoding effort for Draco compression. Higher values reduce file size further but encode more slowly.

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

- **Path**: `settings.dracoCompression.quantizationNormal`
- **Type**: `integer`
- **Min**: `8`
- **Max**: `30`
- **Default**: `14`

Quantization bits for vertex normals. Higher values produce smoother shading at the cost of file size.

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

- **Path**: `settings.dracoCompression.quantizationPosition`
- **Type**: `integer`
- **Min**: `8`
- **Max**: `30`
- **Default**: `16`

Quantization bits for vertex positions. Higher values preserve more positional detail at the cost of file size.

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

- **Path**: `settings.dracoCompression.quantizationTexCoord`
- **Type**: `integer`
- **Min**: `8`
- **Max**: `30`
- **Default**: `14`

Quantization bits for texture coordinates. Higher values keep textures sharper at UV seams at the cost of file size.

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

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

UV chart clustering settings for the output mesh.

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

- **Path**: `settings.meshCluster.globalIterations`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `64`
- **Default**: `1`

Global iterations for chart clustering.

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

- **Path**: `settings.meshCluster.refineIterations`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `64`
- **Default**: `0`

Local refinement iterations for chart clustering.

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

- **Path**: `settings.meshCluster.smoothStrength`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `10`
- **Default**: `1`

Smoothing strength applied during chart clustering.

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

- **Path**: `settings.meshCluster.thresholdConeHalfAngleRad`
- **Type**: `float`
- **Min**: `0`
- **Max**: `3.141592653589793`
- **Default**: `1.5707963267948966`

Cone half-angle threshold in radians used during UV chart clustering.

### [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.

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

- **Path**: `settings.remeshBand`
- **Type**: `float`
- **Max**: `16`
- **Default**: `1`

Narrow-band width in voxels used for dual-contouring remeshing.

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

- **Path**: `settings.remeshProject`
- **Type**: `float`
- **Max**: `1`
- **Default**: `0`

Projection factor for snapping remeshed vertices back to the original surface.

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

- **Path**: `settings.shapeSlat`
- **Type**: `object (6 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`
- **Default**: `12`

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

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

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

End of the sampling schedule fraction over which guidance is applied.

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

- **Path**: `settings.shapeSlat.guidanceIntervalStart`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Default**: `0.6`

Start of the sampling schedule fraction over which guidance is applied.

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

- **Path**: `settings.shapeSlat.guidanceRescale`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Default**: `0.5`

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`
- **Default**: `7.5`

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`
- **Default**: `3`

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 (6 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`
- **Default**: `12`

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

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

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

End of the sampling schedule fraction over which guidance is applied.

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

- **Path**: `settings.sparseStructure.guidanceIntervalStart`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Default**: `0.6`

Start of the sampling schedule fraction over which guidance is applied.

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

- **Path**: `settings.sparseStructure.guidanceRescale`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Default**: `0.7`

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`
- **Default**: `7.5`

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`
- **Default**: `5`

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 (6 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`
- **Default**: `12`

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

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

- **Path**: `settings.texSlat.guidanceIntervalEnd`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Default**: `0.9`

End of the sampling schedule fraction over which guidance is applied.

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

- **Path**: `settings.texSlat.guidanceIntervalStart`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Default**: `0.6`

Start of the sampling schedule fraction over which guidance is applied.

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

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

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`
- **Default**: `1`

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`
- **Default**: `3`

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

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

- **Path**: `settings.textureFormat`
- **Type**: `string`
- **Default**: `WEBP`

Texture format for the output mesh.

**Allowed values**: `WEBP` `PNG`

### [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`

Identifier for the type of task this response belongs to.

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

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

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [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.

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

- **Path**: `outputs.files`
- **Type**: `object (3 properties)`
- **Required**: true

Generated output artifacts.

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

- **Path**: `outputs.files`
- **Type**: `array of objects (2 properties)`
- **Required**: true
- **Min items**: `1`

Generated output files.

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

- **Path**: `outputs.files.uuid`
- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output file.

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

- **Path**: `outputs.files.url`
- **Type**: `string`
- **Required**: true
- **Format**: `uri`

URL of the output file.

## Examples

### image-to-3d (image-to-3d)

[View 3D model](https://assets.runware.ai/examples/microsoft-trellis-2/34ee1b71-7f2d-43f6-9ded-f212d2603693.glb)

```json
{
  "taskType": "3dInference",
  "taskUUID": "5613a9e3-0063-45f2-ae0a-858ba75bcfbb",
  "model": "microsoft:trellis-2@4b",
  "settings": {
    "resolution": 1024,
    "textureSize": 2048,
    "remesh": true
  },
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/e35681d0-7043-4862-9eed-6698b538a1c1.jpg"
  }
}
```

---

### image-to-3d (image-to-3d)

[View 3D model](https://assets.runware.ai/examples/microsoft-trellis-2/260e87d9-77ff-491e-b440-3b1d59556867.glb)

```json
{
  "taskType": "3dInference",
  "taskUUID": "d33c0123-ab89-4944-b8e4-206912b3ebdb",
  "model": "microsoft:trellis-2@4b",
  "settings": {
    "resolution": 1024,
    "textureSize": 2048,
    "remesh": true
  },
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/c3ec2b8a-876e-43fd-a1bf-8d81bfa22c00.jpg"
  }
}
```

---

### image-to-3d (image-to-3d)

[View 3D model](https://assets.runware.ai/examples/microsoft-trellis-2/ab75aeaa-f39d-4d36-a4ae-09e289a74254.glb)

```json
{
  "taskType": "3dInference",
  "taskUUID": "45207280-bb45-45f9-b239-d2815554cb3c",
  "model": "microsoft:trellis-2@4b",
  "settings": {
    "resolution": 1024,
    "textureSize": 2048,
    "remesh": true
  },
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/5b472250-afda-43d5-be68-35ed6e3840a3.jpg"
  }
}
```

---

### image-to-3d (image-to-3d)

[View 3D model](https://assets.runware.ai/examples/microsoft-trellis-2/ee56c952-5321-4cbd-ae2e-d1fe2f026650.glb)

```json
{
  "taskType": "3dInference",
  "taskUUID": "331e6717-e52d-4d5b-a2f3-e7706c692af2",
  "model": "microsoft:trellis-2@4b",
  "settings": {
    "resolution": 1024,
    "textureSize": 2048,
    "remesh": true
  },
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/29d4381c-08b0-4359-851d-fd790502d615.jpg"
  }
}
```