Start building
Use in agenttrellis models

trellis modelsimage generation api

trellis/trellis

Trellis is trellis's image-to-3D AI model. Transform photographs into production-ready 3D meshes with accurate geometry and texture mapping.

Input

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL of the input image to convert to 3D
150
Sampling steps for structured latent generation Range: 1 to 50.
150
Sampling steps for sparse structure generation Range: 1 to 50.
0.90.98
Mesh simplification factor Range: 0.9 to 0.98.
Texture resolution Allowed values: 512, 1024, 2048.
010
Guidance strength for sparse structure generation Range: 0 to 10.
010
Guidance strength for structured latent generation Range: 0 to 10.
Random seed for reproducibility
Idle

Example output — click Run to generate your own

API README

Trellis

Trellis addresses the trellis/trellis workflow for trellis work in image production. The endpoint is especially useful when a project has a defined transformation goal and needs a repeatable request contract instead of an ad-hoc desktop step. Teams can place this named operation inside review, asset preparation, and publishing pipelines while keeping the original request attached to every result. Trellis is trellis's image-to-3D AI model. Transform photographs into production-ready 3D meshes with accurate geometry and texture mapping. Because trellis/trellis is a separate catalog entry, evaluations should use this route’s own inputs, output expectations, and billing behavior. That scope belongs to this named route, not to a neighboring version.

For example, the route documentation includes “https://static.sandbase.ai/examples/trellis/trellis/input_image_0.png”. The mandatory portion is image. seed controls random seed for reproducibility; image controls uRL of the input image to convert to 3D; texture size controls texture resolution; texture size accepts 512, 1024, 2048; mesh simplify controls mesh simplification factor; ss sampling steps controls sampling steps for sparse structure generation; slat sampling steps controls sampling steps for structured latent generation; ss guidance strength controls guidance strength for sparse structure generation. Trellis exposes seed, image, texture_size, mesh_simplify, ss_sampling_steps, slat_sampling_steps, ss_guidance_strength as its documented request surface. Applications can submit that exact shape asynchronously, retain the chosen arguments in job metadata, and collect the resulting media URL for review or publishing.

Highlights

  • Single-image 3D reconstruction. Trellis turns one visual reference into a three-dimensional asset with inferred geometry beyond the visible view.
  • Shape-and-appearance generation. The workflow produces both spatial structure and an associated visual treatment for immediate inspection.
  • Reference-led identity. The source image anchors silhouette, proportions, color, and recognizable object details throughout reconstruction.
  • Rapid concept asset. The result gives visualization and interactive teams a practical base for preview, cleanup, and downstream refinement.

Pricing

Billing optionPrice
Per request$0.020000

When to Use

ScenarioWhy it fits
Choose TrellisUse it when the job specifically calls for trellis and the route’s documented input contract matches assets already available in your workflow.
Keep the request reproducibleUse the required image explicitly, then record optional choices alongside the prompt for repeatable reruns.
Build controlled creative variationsChange one declared control at a time when comparing framing, format, duration, resolution, style, or other route-supported output decisions.
Integrate asynchronous deliveryUse this endpoint when an application can submit work, track completion, and collect the returned media URL instead of requiring an immediate inline artifact.
Validate before a large batchRun representative prompts and source assets first, confirm the visual or audio behavior, then lock the successful request shape for scaled production.

Prompt Guide

Lead with the subject or transformation, then add the composition, environment, style, lighting, motion, voice, or fidelity details relevant to this route. Keep every parameter inside the documented schema; the example below uses only fields declared for trellis/trellis.

{
  "image": "https://static.sandbase.ai/examples/trellis/trellis/input_image_0.png",
  "texture_size": 512
}

Technical Specs

SpecificationDetails
Model IDtrellis/trellis
Execution modeasync
Task typeimage
seedinteger · optional
imagestring · required
texture_sizeinteger · optional · choices: 512, 1024, 2048
mesh_simplifynumber · optional · min 0.9 · max 0.98
ss_sampling_stepsinteger · optional · min 1 · max 50
slat_sampling_stepsinteger · optional · min 1 · max 50
ss_guidance_strengthnumber · optional · min 0 · max 10
slat_guidance_strengthnumber · optional · min 0 · max 10

Related Models

Related Models

trellis/trellis/multiTrellis Multi is trellis's image-to-3D AI model. Transform photographs into production-ready 3D meshes with accurate geometry and texture mapping.trellis/trellis-2/retextureTrellis 2 Retexture is trellis's image-to-3D AI model. Transform photographs into production-ready 3D meshes with accurate geometry and texture mapping.trellis/trellis-2Trellis 2 is trellis's image-to-3D AI model. Transform photographs into production-ready 3D meshes with accurate geometry and texture mapping.