平面图渲染

设计与多媒体 社区 v1.0.0

技能解读

当前原文的自动摘译,尚未人工审校。

输入

名称 · 类型 · 必填 · 默认 · 描述 floor_plan_description · 文本 · 是 · — · 平面图描述(例如“带阳台和开放式厨房的现代两卧室公寓”)。 base_plan_image · image_url · 否 · — · 可选的 2D 平面图图像作为起点。

A 阶段 — 2D 平面图设计

如果未提供{{base_plan_image}},则只需一步提交平面图即可创建二维蓝图: 平面图生成 — muapi image generate(型号=nano-banana-2): 提示:A professional, clean 2D architectural floor plan of {{floor_plan_description}}. Top-down view, technical drawing style, white background, black lines, labeled rooms (Living Room, Kitchen, Bedroom, etc.), high contrast, minimalist design.

B 阶段 — 3D 渲染

2D 计划准备就绪后,提交计划以将其转换为真实的 3D 可视化: 3D 转换 — muapi image edit(模型=nano-banana-2-edit):参考图像:A 阶段的 2D 计划。提示:A stunning, realistic 3D isometric cutaway rendering of the architectural floor plan. Photorealistic textures, warm wooden flooring, modern furniture, soft natural sunlight coming from windows, realistic shadows. High-end architectural visualization, cinematic look, 8k resolution, clean white studio background.

触发关键词

3d floor plan、architectural rendering、2d to 3d plan、house design、interior plan

执行代理人须知

此配方是 LLM 精心策划的:读取每个阶段,收集用户丢失的输入,然后调用 muapi CLI 命令。如果 MUAPI_API_KEY 未设置,请先使用 muapi auth configure。对于还没有 CLI 别名的模型 ID,请通过 curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}' 回退到原始端点,并使用 muapi predict wait <request_id> 进行轮询。

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
设计与多媒体
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
92 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@SamurAIGPT · v1.0.0 · 未声明许可证
上下文用量评级
低消耗
接入复杂程度
需简单配置
是否需要外部接口密钥
需要 · Vendor-specific
兼容的系统
Windows
运行环境要求
未检出明确要求
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
  • 命令执行
网络行为
允许外网请求
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md


# Floor Plan Rendering

**Design a 2D floor plan and convert it into a realistic, high-quality 3D architectural rendering.**

## Inputs

| Name | Type | Required | Default | Description |
|:---|:---|:---|:---|:---|
| `floor_plan_description` | text | yes | — | Description of the floor plan (e.g. "a modern 2-bedroom apartment with a balcony and open kitchen"). |
| `base_plan_image` | image_url | no | — | Optional 2D floor plan image to use as a starting point. |


## Steps

### Phase A — 2D Floor Plan Design

If `{{base_plan_image}}` is not provided, submit the plan with ONE step to create the 2D blueprint:

1. **Floor Plan Generation** — `muapi image generate` (model=`nano-banana-2`):
   - Prompt: `A professional, clean 2D architectural floor plan of {{floor_plan_description}}. Top-down view, technical drawing style, white background, black lines, labeled rooms (Living Room, Kitchen, Bedroom, etc.), high contrast, minimalist design.`
   - Aspect ratio: 4:3 or 1:1

Present the 2D plan to the user for approval.

### Phase B — 3D Rendering

Once the 2D plan is ready, submit the plan to convert it into a realistic 3D visualization:

1. **3D Conversion** — `muapi image edit` (model=`nano-banana-2-edit`):
   - Reference Image: The 2D plan from Phase A.
   - Prompt: `A stunning, realistic 3D isometric cutaway rendering of the architectural floor plan. Photorealistic textures, warm wooden flooring, modern furniture, soft natural sunlight coming from windows, realistic shadows. High-end architectural visualization, cinematic look, 8k resolution, clean white studio background.`
   - Aspect ratio: 4:3 or 1:1

After generation, present the final 3D rendering to the user.

## Trigger Keywords

`3d floor plan`, `architectural rendering`, `2d to 3d plan`, `house design`, `interior plan`


---

## Notes for the Executing Agent

- This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call `muapi` CLI commands. Use `muapi auth configure` first if `MUAPI_API_KEY` is unset.
- For model IDs without a CLI alias yet, fall back to the raw endpoint via `curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` and poll with `muapi predict wait <request_id>`.
- Substitute `{{input_name}}` placeholders with the user's actual inputs before issuing each call.

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。