Skip to main content
Glama

generate_3d

Generate a 3D model from a text description or an uploaded image using connected API nodes. Returns a prompt ID to retrieve the result.

Instructions

Generate a 3D model (glb/obj/fbx) from a text prompt or an input image, using the connected ComfyUI's hosted partner 3D nodes (Tripo, Meshy, Rodin, Hunyuan3D — auto-detected from the server; these are paid API nodes needing a comfy.org API key/login on the server or COMFY_API_KEY here). Builds and enqueues a minimal workflow and returns immediately with the prompt_id — poll get_job_status / get_history for the resulting model file (saved to ComfyUI's output directory). For image mode, upload the image first with upload_image and pass its filename. If the server has no 3D-capable API nodes, returns an actionable error naming local-pack alternatives.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeYes"text" = text-to-3D from prompt; "image" = image-to-3D from an uploaded input image.
nodeNoExplicit 3D API node class_type to use (e.g. "MeshyTextToModelNode"); auto-selected if omitted. Use list_api_nodes with filter "3d" to see options.
imageNoREQUIRED when mode is 'image': ComfyUI input-image filename. Upload local files first with upload_image. (Cross-field requirement enforced at runtime.)
inputsNoProvider-specific extra inputs passed through to the node (e.g. style, texture, quality). Use get_api_node_schema on the chosen node for valid keys.
promptNoREQUIRED when mode is 'text': text description of the 3D model. In mode 'image' it is optional and passed along only if the chosen node accepts a prompt. (Cross-field requirement enforced at runtime — the call fails with a clear error if omitted in text mode.)
disable_random_seedNoIf true, do not randomize seed inputs.
Behavior4/5

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

Since no annotations are provided, the description fully covers behavior: asynchronous (returns prompt_id, poll for result), requires API key, error behavior when no nodes. It does not explicitly state destructiveness, but the generation is non-destructive as it creates new files. The transparency is high.

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?

The description is a single paragraph of 6-7 sentences, front-loaded with the main purpose. It is fairly concise, though could be slightly more structured (e.g., bullet points for steps). Every sentence adds value, no filler.

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

Completeness4/5

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

Given the complexity (6 parameters, async workflow), the description covers the process: building workflow, returning prompt_id, polling for output. It mentions error handling and API key requirement. No output schema is present, but the description explains what to do next. It is fairly complete.

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 100%, yet the description adds value by explaining cross-field requirements (image required when mode='image', prompt when mode='text'), auto-selection of node, and that inputs are provider-specific. It clarifies the runtime behavior beyond the schema.

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?

The description clearly states the tool generates a 3D model from text or image, specifies output formats (glb/obj/fbx), and explains the asynchronous workflow. It differentiates itself by mentioning auto-detected 3D nodes (Tripo, Meshy, etc.) and alternative error handling.

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?

The description provides clear context: text vs image mode, prerequisite to upload image first for image mode, and mentions API key requirements. It also notes that if no 3D-capable nodes, an actionable error with local-pack alternatives is returned. However, it lacks explicit when-not-to-use guidance or direct comparison to sibling tools like generate_image.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/artokun/comfyui-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server