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
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | "text" = text-to-3D from prompt; "image" = image-to-3D from an uploaded input image. | |
| node | No | Explicit 3D API node class_type to use (e.g. "MeshyTextToModelNode"); auto-selected if omitted. Use list_api_nodes with filter "3d" to see options. | |
| image | No | REQUIRED when mode is 'image': ComfyUI input-image filename. Upload local files first with upload_image. (Cross-field requirement enforced at runtime.) | |
| inputs | No | Provider-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. | |
| prompt | No | REQUIRED 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_seed | No | If true, do not randomize seed inputs. |