Skip to main content
Glama

Image to 3D model (3DGen AI)

luw_image_to_3d

Converts a photo of an object into a textured 3D GLB model, with optional extra angles to improve accuracy. Use it to turn furniture, decor, or product images into 3D assets.

Instructions

Luw.ai 3DGen AI: generate a textured 3D model (GLB) from a photo of an object — furniture, decor, products. Add up to 3 photos from other angles for better accuracy. For text-to-3D, first make an image with luw_generate_image. Costs 3 credits (aria) or 8 (symphony, which adds a high-detail texture pack on paid accounts).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "image": "<image>"
    },
    "name": "luw_image_to_3d"
  }
}

Input Schema

NameRequiredDescriptionDefault
imageYesPhoto of the object (public https:// link or data: URI; the local npx server also accepts a file path).
engineNoLuw.ai model: aria (default) or symphony (Symphony-3).
textureNoHigh-detail texture pack: 1 = on (the default with symphony), 0 = off. Symphony engine and paid accounts only.
simplifyNo1 = lighter mesh (150K triangles instead of 500K). Free accounts always get the lighter mesh.
reflectionsNoReflective (PBR) materials. Paid accounts only.
extra_anglesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.3.18
    • changedInput schema / properties / extra_angles / items / description
      Previous value: -"Another angle of the same object (https:// URL, local file path, or data: URI)."New value: +"Another angle of the same object (public https:// link or data: URI; the local npx server also accepts a file path)."
    • changedInput schema / properties / image / description
      Previous value: -"Photo of the object (https:// URL, local file path, or data: URI)."New value: +"Photo of the object (public https:// link or data: URI; the local npx server also accepts a file path)."
    • changedInput schema / properties / reflections / description
      Previous value: -"Enable reflective materials (symphony engine only)."New value: +"Reflective (PBR) materials. Paid accounts only."
    • removedInput schema / properties / seed
      Removed value: -{
      -  "description": "Fix for reproducible results.",
      -  "maximum": 9007199254740991,
      -  "minimum": 0,
      -  "type": "integer"
      -}
    • changedInput schema / properties / simplify / description
      Previous value: -"Mesh simplification level (0 = off, default)."New value: +"1 = lighter mesh (150K triangles instead of 500K). Free accounts always get the lighter mesh."
    • changedInput schema / properties / texture / description
      Previous value: -"Texture size setting (0 = default)."New value: +"High-detail texture pack: 1 = on (the default with symphony), 0 = off. Symphony engine and paid accounts only."
  2. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already disclose the write/open-world, non-idempotent, non-destructive profile, so the description's job is to add operating context — and it does: per-engine credit costs (3 vs 8) and paid-account gating for symphony's texture pack. Some of that overlaps the schema's texture/simplify descriptions, and it does not say whether the call blocks or returns a job to poll.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the capability, then enrichment advice, then routing and cost. Slight redundancy with the schema's own engine/texture wording, but no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 6-parameter generative tool with no output schema, the description covers input, cost, and output format but omits the execution model — whether it returns the model directly or a job handle for luw_get_result. That is the one thing an agent still has to discover empirically.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is high (83%), so the baseline is 3, but the description adds real meaning: extra_angles is framed as 'photos from other angles for better accuracy' with a stated benefit, and engine choice is tied to concrete cost and feature differences rather than just an enum label.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — 'generate a textured 3D model (GLB) from a photo of an object' — and scopes the accepted subject matter (furniture, decor, products). It also names the output format (GLB), which separates it from the image-generation siblings without needing to open the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear usage context: multi-angle photos improve accuracy (up to 3), and text-to-3D requests should first go through luw_generate_image. It does not address when to prefer other 3D-adjacent siblings such as luw_sketch_to_render, so the alternative routing is helpful but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.