Skip to main content
ModelRunner
luma avatar

Luma Uni-1 API

luma/uni-1

Generate a single high-quality image from a text prompt — a well-rounded default with optional manga styling, web-grounded references, and up to nine guidance images.

0.042
OpenAPI

Model Input

Input

The text prompt describing the image to generate.

The aspect ratio of the generated image.

Additional Settings

Customize your input with more control.

The visual style of the generated image.

The output image format.

If true, the model may consult the web while generating.

You need to be logged in to run this model and view results.
Log in

Model Output

Output

Generated image output
Generated in 47.722 seconds
Logs (1 lines)

Model Example Requests

Examples

Example output 1Example output 2Example output 3

Luma Uni-1 API

Luma Uni-1 is a text-to-image AI model by luma. On ModelRunner it runs through a REST API or via MCP from any AI assistant, at $0.042 per image.

POST https://queue.modelrunner.run/luma/uni-1

cURL

# 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/luma/uni-1 \
  -H "Authorization: Key $MRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "style": "auto",
    "prompt": "a tranquil zen garden with raked sand and a single maple leaf, soft morning light",
    "aspect_ratio": "1:1",
    "output_format": "jpeg",
    "enable_web_search": false,
    "reference_image_urls": null,
    "metadata": {
      "project": "my-project"
    }
  }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }

# Poll status_url until "COMPLETED", then fetch the result
curl "https://queue.modelrunner.run/luma/uni-1/requests/$REQUEST_ID/status" \
  -H "Authorization: Key $MRUN_API_KEY"
curl "https://queue.modelrunner.run/luma/uni-1/requests/$REQUEST_ID" \
  -H "Authorization: Key $MRUN_API_KEY"

JavaScript

import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("luma/uni-1", {
  input: {
    "style": "auto",
    "prompt": "a tranquil zen garden with raked sand and a single maple leaf, soft morning light",
    "aspect_ratio": "1:1",
    "output_format": "jpeg",
    "enable_web_search": false,
    "reference_image_urls": null
  },
});
console.log(result);

Python

import os
import requests

headers = {"Authorization": f"Key {os.environ['MRUN_API_KEY']}"}

submitted = requests.post(
    "https://queue.modelrunner.run/luma/uni-1",
    headers=headers,
    json={
      "style": "auto",
      "prompt": "a tranquil zen garden with raked sand and a single maple leaf, soft morning light",
      "aspect_ratio": "1:1",
      "output_format": "jpeg",
      "enable_web_search": false,
      "reference_image_urls": null
    },
).json()

# Poll submitted["status_url"] until "COMPLETED", then:
result = requests.get(submitted["response_url"], headers=headers).json()

Input parameters

NameTypeRequiredDescription
promptstringyesThe text prompt describing the image to generate.
aspect_ratioenumnoThe aspect ratio of the generated image. Default: null.
styleenumnoThe visual style of the generated image. Default: "auto".
output_formatenumnoThe output image format. Default: null.
enable_web_searchbooleannoIf true, the model may consult the web while generating. Default: false.
reference_image_urlsarraynoOptional list of reference image URLs to steer composition (up to 9). Default: null.

Machine-readable: OpenAPI schema · llms.txt

Use Luma Uni-1 from Claude & Cursor (MCP)

Point Claude Code, Claude Desktop, Cursor, or any MCP client at the ModelRunner MCP server and Luma Uni-1 becomes a tool your assistant can call directly — it authorizes via OAuth (no API key in config) and runs this model with the run_model tool using the endpoint luma/uni-1.

MCP client config (Claude Desktop, Cursor)

{
  "mcpServers": {
    "modelrunner": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.modelrunner.run/mcp"]
    }
  }
}

Claude Code

claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcp

Then ask your assistant, for example: “Run luma/uni-1 on ModelRunner to generate image”. MCP setup guide.

Model Details

Model Details

Uni-1 is the standard tier of the Uni-1 family and the sensible default for text-to-image work: give it a prompt and it returns a single, polished image, generated faster and more cheaply than the Max tier. It carries the full Uni-1 feature set — `auto` or `manga` styling, optional web-grounded references, and up to nine reference images to steer the result — so you trade only headroom on the very hardest prompts, not capability. Reach for it whenever you want a strong result without paying for a hero-grade render.

## Best for - Everyday single images and quick iteration where cost and speed matter - Faithful rendering of clear, specific prompts at any of the supported aspect ratios - Black-and-white manga and comic line-art via the `manga` style - Illustrations that should reflect real, recent, or niche subjects using web-grounded references - Generations steered by your own reference images for composition, subject, or style

## Choose another model when - You need maximum fidelity and the strongest prompt adherence on a single hero shot and can accept higher cost — use `luma/uni-1-max` - You want to edit or transform an existing image rather than generate one from a prompt — use an image-to-image or image-editing model - You need motion or video output — use a video model

## Tips - Write clear, specific prompts; this tier rewards precise wording. - Use `manga` only when you want inked line-art — `auto` covers photoreal and most illustrative looks. - Step up to `luma/uni-1-max` when one hero image needs the highest possible detail.

## Advanced Configuration - `style` — `auto` (default) picks a fitting photoreal or illustrative look; `manga` produces black-and-white manga / comic line-art for paneled illustration and inked characters. - `enable_web_search` — set `true` to let the model consult the web for visual references while generating, useful when your prompt names real, recent, or niche subjects; leave `false` (default) for faster, self-contained generation. - `reference_image_urls` — pass up to nine image URLs to guide composition, subject, or style toward your own references; the model blends them with the prompt.

To run via the ModelRunner JavaScript client: ```js import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("luma/uni-1", { input: { prompt: "a lighthouse on a cliff at golden hour, dramatic sky", aspect_ratio: "16:9", style: "auto", }, }); ```