Redesign outdoor spaces — gardens, yards, balconies — from a single photo with controllable style, palette, lighting, season, and sky.
| Base Model | Pricing Mode | Effective Cost |
|---|---|---|
| nano-banana-2/editdefault | megapixel tiered | Tiered pricing |
| nano-banana | per output | $0.039 |
Landscape Redesign is a image-to-image AI wrapper by roomix. On ModelRunner it runs through a REST API or via MCP from any AI assistant with pay-per-use pricing.
# Submit a request to the queue. Input fields go at the top level of the
# body. The optional reserved "metadata" object holds your own flat string
# tags — stored on the request, never sent to the model; filter later with
# GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>.
curl -X POST https://queue.modelrunner.run/roomix/landscape-redesign \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"sky": "clear",
"color": "forest-inspired",
"style": "japanese-zen",
"season": "autumn",
"daylight": "sunset",
"file_url": "https://media.modelrunner.ai/zI3AEchYMetGS9pk-source-8CFEE305-8A0D-4D19-9772-D6A25595FAB7.jpg",
"creativity": "balanced",
"creativity_level": 0.7,
"metadata": {
"project": "my-project"
}
}'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }
# Poll status_url until "COMPLETED", then fetch the result
curl "https://queue.modelrunner.run/roomix/landscape-redesign/requests/$REQUEST_ID/status" \
-H "Authorization: Key $MRUN_API_KEY"
curl "https://queue.modelrunner.run/roomix/landscape-redesign/requests/$REQUEST_ID" \
-H "Authorization: Key $MRUN_API_KEY"import { modelrunner } from "@modelrunner/client";
const result = await modelrunner.subscribe("roomix/landscape-redesign", {
input: {
"sky": "clear",
"color": "forest-inspired",
"style": "japanese-zen",
"season": "autumn",
"daylight": "sunset",
"file_url": "https://media.modelrunner.ai/zI3AEchYMetGS9pk-source-8CFEE305-8A0D-4D19-9772-D6A25595FAB7.jpg",
"creativity": "balanced",
"creativity_level": 0.7
},
});
console.log(result);import os
import requests
headers = {"Authorization": f"Key {os.environ['MRUN_API_KEY']}"}
submitted = requests.post(
"https://queue.modelrunner.run/roomix/landscape-redesign",
headers=headers,
json={
"sky": "clear",
"color": "forest-inspired",
"style": "japanese-zen",
"season": "autumn",
"daylight": "sunset",
"file_url": "https://media.modelrunner.ai/zI3AEchYMetGS9pk-source-8CFEE305-8A0D-4D19-9772-D6A25595FAB7.jpg",
"creativity": "balanced",
"creativity_level": 0.7
},
).json()
# Poll submitted["status_url"] until "COMPLETED", then:
result = requests.get(submitted["response_url"], headers=headers).json()| Name | Type | Required | Description |
|---|---|---|---|
| sky | enum | no | Preferred sky conditions. Default: "auto". |
| color | enum | no | Preferred color palette. Default: "auto". |
| style | enum | no | Landscape style. Uses the same enum values as the room-redesign wrapper but reinterpreted for outdoor scenes. Default: "no-style". |
| prompt | string | no | Optional additional user instructions. |
| season | enum | no | Seasonal atmosphere. Default: "auto". |
| daylight | enum | no | Preferred lighting / time-of-day mood. Default: "auto". |
| file_url | string (uri) | yes | External URL of the source outdoor photo to redesign. |
| creativity | enum | yes | How strongly to preserve the original versus reinterpret it. Default: "undefined". |
| creativity_level | number | no | Fine-grained creativity value (only meaningful when creativity is precise). Default: 0.7. |
Machine-readable: OpenAPI schema · llms.txt
Point Claude Code, Claude Desktop, Cursor, or any MCP client at the ModelRunner MCP server and Landscape Redesign becomes a tool your assistant can call directly — it authorizes via OAuth (no API key in config) and runs this wrapper with the run_model tool using the endpoint roomix/landscape-redesign.
{
"mcpServers": {
"modelrunner": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.modelrunner.run/mcp"]
}
}
}claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcpThen ask your assistant, for example: “Run roomix/landscape-redesign on ModelRunner to generate image”. MCP setup guide.
Reimagine an outdoor space from one photo. Pick a garden style, color palette, daylight, season, and sky, and the wrapper composes a detailed prompt for the underlying image-edit model. Use `prompt` for additional free-text guidance. Designed for landscape-flavored variants of the same style enum used by the room-redesign wrapper, so the same UI can drive both.