Skip to main content
skill CX Codex

muapi-interior-design-visualizer — Claude Code skill: interior design

Generates an empty room, then fills it with furniture and decor. Or redesigns a room you already have a photo of.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add SamurAIGPT/Generative-Media-Skills --skill muapi-interior-design-visualizer -a claude-code
npx skills add SamurAIGPT/Generative-Media-Skills --skill interior-design-visualizer -a claude-code
Open on GitHub

What muapi-interior-design-visualizer does

Two phases. First the skill generates an empty room with muapi image generate using the gpt-image-2-text-to-image model — all it needs is a room type and a style. Then it takes that image as a reference and furnishes it through muapi image edit with nano-banana-2-edit: sofa, coffee table, rug, plants, lighting. If you already have a photo of an empty room, phase one is skipped and your image goes straight into the edit call.

Before you start, you need a MUAPI_API_KEY and the muapi CLI. If the variable is unset, run muapi auth configure first. For model IDs that have no CLI alias yet, the skill suggests falling back to the raw endpoint with curl and polling via muapi predict wait <request_id>.

Every input is optional: room_type defaults to modern living room, design_style to contemporary minimalist. Each call spends API credits, so a run of style variations is a run of requests. The skill offers to switch styles after the first render, but that call is yours to make.

What it helps with

  • generate an empty room in a specific style
  • furnish a room with furniture and decor
  • redesign a room from an existing photo
  • produce several style variants of one space
  • show a client what a renovation could look like

Example prompts for the agent

  • generate an empty bedroom in Scandinavian style
  • furnish this room with industrial-style furniture
  • redesign the interior in this photo and make it more modern

How to install muapi-interior-design-visualizer

1Skills CLI (Vercel)

npx skills add SamurAIGPT/Generative-Media-Skills --skill muapi-interior-design-visualizer -a claude-code
npx skills add SamurAIGPT/Generative-Media-Skills --skill interior-design-visualizer -a claude-code

2Manually: put the files in place

~/.claude/skills/interior-design-visualizer/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/interior-design-visualizer/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about muapi-interior-design-visualizer

How do I install muapi-interior-design-visualizer in Claude?

Run npx skills add SamurAIGPT/Generative-Media-Skills --skill interior-design-visualizer -a claude-code. The skill file then lives at ~/.claude/skills/interior-design-visualizer/SKILL.md.

What does muapi-interior-design-visualizer do?

It generates an empty room from a room type and style, then fills it with furniture and decor through an image edit call. You can also supply your own empty-room photo instead of generating one.

What do I need for the skill to work?

A MUAPI_API_KEY and the muapi CLI. If the variable is unset, run muapi auth configure.

Source text

SKILL.md · MIT
---
slug: muapi-interior-design-visualizer
name: muapi-interior-design-visualizer
version: "1.0.0"
description: Visualize interior design by generating an empty room and filling it with stylish furniture and decor, or by redesigning an existing room.
acceptLicenseTerms: true
---


# Interior Design Visualizer

**Visualize interior design by generating an empty room and filling it with stylish furniture and decor, or by redesigning an existing room.**

## Inputs

| Name | Type | Required | Default | Description |
|:---|:---|:---|:---|:---|
| `room_type` | text | no | modern living room | The type of room to design (e.g. living room, bedroom, office). |
| `design_style` | text | no | contemporary minimalist | The aesthetic style (e.g. Scandinavian, Industrial, Bohemian). |
| `empty_room_image` | image_url | no | — | Optional image of an empty room to be used as a base. |


## Steps

### Phase A — Room Setup

If `{{empty_room_image}}` is not provided, submit the plan with ONE step to generate an empty base room:

1. **Empty Room Generation** — `muapi image generate` (model=`gpt-image-2-text-to-image`):
   - Prompt: `A professional wide-angle photograph of a completely empty {{room_type}} with {{design_style}} architecture. Large windows with natural light, clean wooden or tiled flooring, white or neutral-colored walls, no furniture, high ceiling. High-quality architectural photography, cinematic look.`
   - Aspect ratio: 4:3 or 1:1

Present the empty room to the user.

### Phase B — Furnishing & Styling

Once the base room is ready, submit the plan to fill it with furniture:

1. **Room Furnishing** — `muapi image edit` (model=`nano-banana-2-edit`):
   - Reference Image: The empty room image from Phase A (or the user-provided `{{empty_room_image}}`).
   - Prompt: `A stunningly designed {{room_type}} filled with high-end furniture in a {{design_style}} style. Includes a comfortable sofa, stylish coffee table, elegant rug, indoor plants, decorative wall art, and ambient lighting. The furniture placement is natural and architecturally sound. Photorealistic textures, soft lighting, cozy and inviting atmosphere, 8k resolution.`
   - Aspect ratio: Same as the base image.

After generation, present the final interior design visualization to the user. You can offer to generate variations with different styles (e.g., "Change style to Industrial").

## Trigger Keywords

`interior design`, `room visualizer`, `furniture design`, `home decor`, `redesign room`


---

## 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.

© SamurAIGPT · MIT · SamurAIGPT/Generative-Media-Skills

Similar skills

Everything for Design →

From the same set32

muapi-3d-logo-animation Turn a 2D logo into a 3D image, review it, then generate a cinematic animation. Use it to make a logo reveal from an existing logo file. CX Codex +1 666installs muapi-amazon-product-listing Generates four images for an Amazon product listing: a white-background hero, a lifestyle shot, a feature infographic and a macro detail closeup. CX Codex +1 666installs muapi-multi-angle-reshoot Re-renders one subject or scene from several camera angles — bird's eye, fish-eye, low angle, macro — keeping face, clothing and detail intact. CX Codex +1 665installs muapi-interior-design Generates and redesigns interiors: a room concept from text or a rework of an existing photo. Useful when you need a render without opening a 3D editor. CX Codex +1 665installs muapi-one-shot-video Builds the prompt and fires off a single uncut cinematic shot: no transitions, camera motion, dramatic lighting. CX Codex +1 664installs muapi-fashion-try-on This skill puts a garment from one photo onto a person from another, then optionally turns the result into a fashion video. CX Codex +1 663installs muapi-jewelry-product-video Turns a jewelry item into a short luxury commercial: one hero frame first, then macro animation of the stone. Useful when you need product video without a shoot. CX Codex +1 663installs muapi-music-video Turns a song theme into keyframes, animated scenes, and a matching music track. Use it to build a short video story or visualize a song. CX Codex +1 663installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor