OpenClaw

AI 3D Generation

Create, convert, and download AI-generated 3D models using Neural4D APIs. Optimized for commercial pipelines.

6e6e6e0 来源安装数☆ 0 仓库 Starsv1.0.0

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install 6e6e6e/ai-3d-generation

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

Setup

On first use, ensure the NEURAL4D_API_TOKEN environment variable is set. All API requests must include the header: Authorization: Bearer <YOUR_TOKEN>.

When to Use

Use this skill when generating 3D models from text prompts or images using DreamTech's Neural4D engine. This is particularly suited for creating assets where precise format conversions (like .stl, .obj, .fbx) and physical dimensions are required for manufacturing workflows.

Core Rules & Cost Guardrails

1. Point Consumption Awareness

Always track API point costs before executing bulk runs:

Text to 3D: 20 points per operation.
Image to 3D: 20 points per operation.
Chibi-style Generation: 30 points per operation.
Format Conversion: 10 points per operation.
You can query the remaining balance at /api/queryPointsInfo.

2. Asynchronous Polling Contract

Model generation is asynchronous. You must poll for completion:

Query /api/retrieveModel using the uuid.
Check codeStatus:
- 0: Generation complete.
- 1: Generating (Wait and poll again).
- -3: Generation failed.

Workflow Pipelines

Pipeline A: Text to 3D

Request: POST https://alb.neural4d.com:3000/api/generateModelWithText.
- Payload: {"prompt": "...", "modelCount": 4, "disablePbr": 0}.
Retrieve: Extract uuids from the response.
Poll: Call /api/retrieveModel with the uuid until codeStatus is 0.
Download: Extract modelUrl and download the .glb asset.

Pipeline B: Image to 3D (Strict 3-Step Process)

Matting: Submit the image (JPG/PNG, <10MB, 256x256 to 6048x8064) via multipart/form-data to /api/mattingImage. Extract the requestId.
Get Matting Result: Send the requestId to /api/getMattedResult. Extract a preferred fileKey from the response.
Generate: Send the fileKey to /api/generateModelWithImage to start generation and receive uuids.
Poll: Use /api/retrieveModel to poll...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/6e6e6e/ai-3d-generation
Version: 1.0.0
Commit: bdc029b05079f878e0cafed11117d7feeb2255c6
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

## Setup

On first use, ensure the `NEURAL4D_API_TOKEN` environment variable is set.
All API requests must include the header: `Authorization: Bearer <YOUR_TOKEN>`.

## When to Use

Use this skill when generating 3D models from text prompts or images using DreamTech's Neural4D engine. This is particularly suited for creating assets where precise format conversions (like `.stl`, `.obj`, `.fbx`) and physical dimensions are required for manufacturing workflows.

## Core Rules & Cost Guardrails

### 1. Point Consumption Awareness
Always track API point costs before executing bulk runs:
- **Text to 3D:** 20 points per operation.
- **Image to 3D:** 20 points per operation.
- **Chibi-style Generation:** 30 points per operation.
- **Format Conversion:** 10 points per operation.
- You can query the remaining balance at `/api/queryPointsInfo`.

### 2. Asynchronous Polling Contract
Model generation is asynchronous. You must poll for completion:
- Query `/api/retrieveModel` using the `uuid`.
- Check `codeStatus`:
  - `0`: Generation complete.
  - `1`: Generating (Wait and poll again).
  - `-3`: Generation failed.

## Workflow Pipelines

### Pipeline A: Text to 3D
1. **Request:** `POST https://alb.neural4d.com:3000/api/generateModelWithText`.
   - Payload: `{"prompt": "...", "modelCount": 4, "disablePbr": 0}`.
2. **Retrieve:** Extract `uuids` from the response.
3. **Poll:** Call `/api/retrieveModel` with the `uuid` until `codeStatus` is `0`.
4. **Download:** Extract `modelUrl` and download the `.glb` asset.

### Pipeline B: Image to 3D (Strict 3-Step Process)
1. **Matting:** Submit the image (JPG/PNG, <10MB, 256x256 to 6048x8064) via `multipart/form-data` to `/api/mattingImage`. Extract the `requestId`.
2. **Get Matting Result:** Send the `requestId` to `/api/getMattedResult`. Extract a preferred `fileKey` from the response.
3. **Generate:** Send the `fileKey` to `/api/generateModelWithImage` to start generation and receive `uuids`.
4. **Poll:** Use `/api/retrieveModel` to poll...

搜索