Logo
Get Started
Profile

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.

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

preview
Generated in 47.722 seconds
Logs (1 lines)

Model Example Requests

Examples

ST75ZewuibZp7GrqeckvP9mEzFtk3X4rc4sL3lVgTIZG9Xh3kwb8RCABABY0ufl

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", }, }); ```