MicrosoftMediumHigh

TRELLIS

Microsoft's TRELLIS image-to-3D (836K+ runs — the most-used 3D model on Replicate). Turns one or more images into a textured GLB 3D asset, with turntable render videos and optional Gaussian PLY.

77 credits

per generation

The most-used 3D model on Replicate

Single or multi-image input

Textured GLB export (generate_model)

Color/normal turntable render videos

Gaussian point cloud PLY export

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "firtoz/trellis",
  "input": {
    "images": [
      "https://example.com/product.png"
    ],
    "generate_model": true,
    "texture_size": 1024
  }
}'

Parameters

Parameter	Type	Required	Default	Description
`images`	array	Yes	-	One or more images of the object (multiple angles improve quality)
`seed`	integer	No	0	Random seed (randomize_seed overrides)
`randomize_seed`	boolean	No	true	Randomize seed
`generate_color`	boolean	No	true	Generate a color turntable render video
`generate_normal`	boolean	No	false	Generate normal video render
`generate_model`	boolean	No	false	Generate the textured GLB 3D model file
`save_gaussian_ply`	boolean	No	false	Save Gaussian point cloud as PLY file
`return_no_background`	boolean	No	false	Return the preprocessed images without background
`ss_guidance_strength`	number	No	7.5	Stage 1: Sparse Structure Generation - Guidance Strength
`ss_sampling_steps`	integer	No	12	Stage 1: Sparse Structure Generation - Sampling Steps
`slat_guidance_strength`	number	No	3	Stage 2: Structured Latent Generation - Guidance Strength
`slat_sampling_steps`	integer	No	12	Stage 2: Structured Latent Generation - Sampling Steps
`mesh_simplify`	number	No	0.95	Mesh simplification ratio for the GLB
`texture_size`	integer	No	1024	GLB texture resolution (when generate_model is true)

How to Provide File Input

There are 3 ways to provide files for the images parameter:

Recommended

Direct Upload (Multipart)

Attach files directly to POST /v1/predictions/upload. No separate upload step needed.

curl -X POST "https://api.core.today/v1/predictions/upload" \
  -H "X-API-Key: cdt_your_api_key" \
  -F "model=firtoz/trellis" \
  -F 'input={"prompt":"your prompt here"}' \
  -F "file:images=@your_file.png"

Image URL

Pass a publicly accessible URL directly. You can also use file_url from the Storage API.

{
  "model": "firtoz/trellis",
  "input": {
    "prompt": "your prompt here",
    "images": ["https://example.com/image.jpg"]
  }
}

See the File Upload docs for more upload methods including Presigned URLs.

Common Parameters

Common parameters used when calling POST /v1/predictions.

Parameter	Type	Required	Default	Description
`model`	string	Yes	-	Model identifier
`input`	object	Yes	-	Object containing the model-specific parameters from the table above
`output_folder`	string	No	-	Folder path for output files (max 256 chars, '..' not allowed)
`webhook_url`	string	No	-	Webhook URL to call on completion
`is_public`	boolean	No	false	If true, output files are also available via permanent public URLs

Examples

Product Photo to GLB

Create a textured 3D model from a single product photo

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "firtoz/trellis",
  "input": {
    "images": [
      "https://example.com/product.png"
    ],
    "generate_model": true,
    "texture_size": 1024
  }
}'