Trellis 2 Image To 3d API Documentation

Trellis 2 Image To 3d API Documentation

Playground

TRELLIS.2 Image-to-3D turns a single reference image into a textured 3D GLB model with PBR materials for game assets, product visualization, 3D design, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

TRELLIS.2 Image to 3D turns a single input image into a textured 3D GLB model with PBR materials. Upload a clear image of one object, choose generation resolution, texture size, face-count target, and background handling, then generate a 3D asset for visualization, games, prototyping, or further editing.

Why Choose This?

• Single-image 3D generation
  Create a textured 3D model from one input image.

• PBR material output
  Generate GLB assets with embedded UVs, base-color textures, and metallic/roughness materials.

• Resolution control
  Choose 512, 1024, or 1536 depending on cost, speed, and detail needs.

• Texture-size options
  Select 1024, 2048, or 4096 texture size for different asset-quality requirements.

• Face-count control
  Set a target face count to guide mesh simplification for downstream workflows.

• Background removal option
  Use remove_background to clean the input before 3D generation.

Parameters

How to Use

1. Upload one image — Provide a clear image of a single object.
2. Choose resolution — Use 512 for lower-cost drafts, 1024 for standard generation, or 1536 for higher-detail output.
3. Choose texture size — Use 1024 or 2048 for standard textures, or 4096 when higher texture detail is needed.
4. Set face count optional — Adjust target_face_count based on your geometry-detail or optimization needs.
5. Configure background removal optional — Keep remove_background enabled when the object should be separated from its background.
6. Set seed optional — Use a fixed seed for reproducible results, or -1 for random generation.
7. Submit — Generate the 3D model and retrieve the GLB output.

Pricing

Pricing is based on selected resolution and whether texture_size is set to 4096.

texture_size values of 1024 and 2048 do not add a separate charge. Selecting 4096 adds $0.05.

target_face_count, remove_background, and seed do not add separate charges.

Best Use Cases

• Image-to-3D asset creation — Convert a single object image into a textured 3D model.
• Game and real-time assets — Generate starting meshes for downstream optimization or editing.
• Product visualization — Turn product images into 3D assets for previews and presentations.
• Creative prototyping — Explore object forms and 3D concepts from image references.
• Design workflows — Generate editable GLB assets for 3D applications and viewers.

Pro Tips

• Use a clear, well-lit image with one main object.
• Avoid cluttered backgrounds, heavy shadows, reflections, occlusion, or motion blur.
• Keep remove_background enabled when the object should be isolated before generation.
• Use 512 for quick tests and 1536 when higher detail matters.
• Use 4096 texture size when the model needs more detailed surface appearance.
• Lower target_face_count for lighter assets and higher values when detail preservation matters.
• Inspect the GLB from multiple angles before using it in production.

Notes

• image is required.
• This endpoint supports single-image input only.
• Text-only generation and multi-view image input are not supported.
• The output is a generated 3D interpretation, not an exact 3D scan.
• The mesh is not guaranteed to be watertight.
• Higher resolution and larger texture size may take longer to generate.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "resolution": "1024",
  "texture_size": 2048,
  "target_face_count": 200000,
  "remove_background": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/trellis-2/image-to-3d" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters