Microsoft Trellis 2

From 300 credits/call
ae_trellis_2

Turn a single image into a textured 3D GLB model, with options to balance detail, mesh quality, and file size.

Image
From 300 credits/call

Pricing

From 300 credits/call
ResolutionCharge
512300 credits/call
1024 / Not specified360 credits/call
1536420 credits/call

Starting price applies to Resolution: 512.

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
request_bodyobjectYesNo parameter description.—
request_body.seedinteger | unknownNoRandom seed for reproducibility—
request_body.remeshbooleanNoRebuild the mesh topology for cleaner triangles. Slower but usually produces better results for downstream use (animation, 3D printing, etc).true
request_body.image_urlstringYesURL of the input image to convert to 3D—
request_body.resolutionenum (512 | 1024 | 1536)NoOutput resolution; higher is slower but more detailed1024
request_body.remesh_bandnumberNoControls how far remeshing can move vertices from the original surface. Higher values allow more smoothing but may lose fine details.1
request_body.ss_rescale_tnumberNoControls noise schedule sharpness for structure generation. Higher values produce sharper transitions.5
request_body.texture_sizeenum (1024 | 2048 | 4096)NoResolution of the texture image baked onto the mesh. Higher values capture finer surface details but produce larger files.2048
request_body.remesh_projectnumberNoHow much to project remeshed vertices back onto the original surface. 0 = no projection (smoother), 1 = full projection (preserves detail).0
request_body.decimation_targetintegerNoTarget number of vertices in the final mesh. Lower values produce smaller files but less detail. 500k is good for most uses, reduce to 20k-50k for web/mobile.500000
request_body.ss_sampling_stepsintegerNoNumber of denoising steps for the initial structure. More steps = slower but potentially higher quality.12
request_body.tex_slat_rescale_tnumberNoControls noise schedule sharpness for texture generation. Higher values produce sharper texture details.3
request_body.ss_guidance_rescalenumberNoDampens artifacts from high guidance in stage 1. Lower values allow stronger guidance effects, higher values stabilize the output.0.7
request_body.shape_slat_rescale_tnumberNoControls noise schedule sharpness for shape refinement. Higher values produce sharper geometric details.3
request_body.ss_guidance_strengthnumberNoHow closely the initial 3D structure follows the input image. Higher values produce more faithful but potentially noisier results.7.5
request_body.tex_slat_sampling_stepsintegerNoNumber of denoising steps for texture generation. More steps = slower but potentially cleaner textures.12
request_body.shape_slat_sampling_stepsintegerNoNumber of denoising steps for shape refinement. More steps = slower but potentially smoother geometry.12
request_body.tex_slat_guidance_rescalenumberNoDampens artifacts from high guidance in the texture stage. Increase if textures look noisy or have color banding.0
request_body.tex_slat_guidance_strengthnumberNoHow closely the texture follows the input image colors. Higher values produce more vivid but potentially oversaturated textures.1
request_body.shape_slat_guidance_rescalenumberNoDampens artifacts from high guidance in the shape stage. Increase if you see noisy geometry.0.5
request_body.shape_slat_guidance_strengthnumberNoHow closely the detailed geometry follows the input image. Higher values add more detail but may introduce noise.7.5

Invocation example

Copy the request and explore its response example.

POST/agent-api/v1/tool/executeX-Api-Key

Submit first, then query with the returned task_id until the task completes.

Request coderequest.sh
curl --request POST \
  --url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_trellis_2' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "decimation_target": 120000,
      "image_url": "https://agentearth.ai/fileserver/file/e526a548-99f9-4088-a924-85d9fea088ce.jpg",
      "remesh": true,
      "resolution": 1024,
      "texture_size": 2048
    }
  }
}'
Response exampleresponse.json
JSON
{
  "description": "task accepted; poll the result via query_tool with this task_id",
  "query_tool": "ae_get_result",
  "status": "created",
  "task_id": "bfc1a9e0-6721-4930-aab7-bddbbe56484a"
}

Guides using this tool

See how this tool fits into real workflows