# Uni-1 Max

Uni-1 Max is the higher-quality tier of Luma's Uni-1 image model. Luma's API docs say "Uni-1 Max produces higher-quality output than Uni-1" and that the two share the same parameter set, differing in quality and per-image price. In Sloosh it makes 2K images from a prompt and up to 9 reference images.

Web page: https://sloosh.ai/models/uni-1-max

[Use Uni-1 Max](https://sloosh.ai/studio/image?image-model=uni-1-max)

## Key facts in Sloosh

|   |   |
| --- | --- |
| Made by | Luma |
| Makes | image |
| Inputs | text, up to 9 reference images |
| Resolution | 2K |
| Aspect ratios | Auto, 16:9, 3:2, 1:1, 2:3, 9:16 (default Auto) |
| Prompt limit | 6,000 characters |

## Best for

- Final images after you settle the idea on Uni-1: Luma says Max produces higher-quality output with the same parameters ([Luma API docs](https://docs.agents.lumalabs.ai/guides/model/)).
- Reference-guided images that keep identity, composition or style from up to nine inputs ([Luma](https://lumalabs.ai/news/uni-1-1-api)).
- Text on signs, labels and covers, and spatial logic for shadows and perspective, shared with Uni-1 ([Luma API docs](https://docs.agents.lumalabs.ai/guides/model/)).

## How to use Uni-1 Max in Sloosh

1. Open [Uni-1 Max in Studio](https://sloosh.ai/studio/image?image-model=uni-1-max).
2. Add up to 9 references and give each a role.
3. Describe the final image with concrete terms (lens, light, named style), text in quotes.
4. Leave the ratio on Auto or pick one. Output is 2K.
5. Press Generate; the price shows first. A common pattern is to find the idea on Uni-1, then render the final on Uni-1 Max with the same prompt (both take the same settings).

## Uni-1 Max prompting tips

- Luma says Uni-1 and Uni-1 Max use the same parameters, so prompts move between them unchanged ([Luma API docs](https://docs.agents.lumalabs.ai/guides/model/)).
- Give every reference a role: "Use IMAGE1 (description) as a [ROLE] reference" ([Luma start guide](https://lumalabs.ai/learning-hub/luma-uni-1-model)).
- "Put exact text in quotes in your prompt" ([Luma API docs](https://docs.agents.lumalabs.ai/guides/model/)).
- Use specific, named aesthetics; "Precision beats generality" ([Luma start guide](https://lumalabs.ai/learning-hub/luma-uni-1-model)).

## Uni-1 Max example prompts

**Prompt 1**

```text
Use IMAGE1 (a matte black water bottle) as a product reference. A hero shot of the bottle on a mossy rock beside a mountain stream at golden hour, water droplets on the surface, 85mm lens, shallow depth of field. Keep the bottle's logo exactly as in IMAGE1.
```

**Prompt 2**

```text
A film-noir style poster: a detective in a trench coat under a single streetlamp, long shadows on wet cobblestones, the title "Midnight Ledger" in tall art deco letters at the top.
```

**Prompt 3**

```text
Use IMAGE1 (a woman with short silver hair) as a character reference. A magazine cover portrait of her in a white studio, soft key light from the left, the masthead "NORTH" across the top.
```

## How it compares in Sloosh

| Model | Resolution | References | Prompt limit |
| --- | --- | --- | --- |
| Uni-1 Max | 2K | 9 | 6,000 |
| [Uni-1](https://sloosh.ai/models/uni-1) | 2K | 9 | 6,000 |
| [Nano Banana Pro](https://sloosh.ai/models/gemini-3-pro-image-preview) | 1K, 2K, 4K | 14 | 50,000 |

Max is the finishing tier of the pair; the specs in Sloosh match Uni-1, the difference is output quality.

## Where else it runs

The Luma API (Uni-1.1 Max, from 5 May 2026, per [Luma](https://lumalabs.ai/news/uni-1-1-api)).

## Frequently asked questions

### What is Uni-1 Max?

The higher-quality tier of Luma's Uni-1 image model, with the same inputs as Uni-1.

### Uni-1 Max vs Uni-1?

Same parameters and inputs; Luma says Max gives higher-quality output at a higher per-image price. Use [Uni-1](https://sloosh.ai/models/uni-1) to explore and Max for the final.

### How many references does Uni-1 Max take?

Up to 9 in Sloosh.

### What resolution does Uni-1 Max make?

2K.

### Which aspect ratios does Uni-1 Max support in Sloosh?

Auto, 16:9, 3:2, 1:1, 2:3 and 9:16, with prompts up to 6,000 characters.

## Related

- Models: [Uni-1](https://sloosh.ai/models/uni-1), [Nano Banana Pro](https://sloosh.ai/models/gemini-3-pro-image-preview)
- Answers: [What is the best AI image model in 2026?](https://geo.sloosh.ai/posts/what-is-the-best-ai-image-model-in-2026)

## Sources

- [Luma API docs: Models](https://docs.agents.lumalabs.ai/guides/model/)
- [Luma: Introducing the Uni-1.1 API](https://lumalabs.ai/news/uni-1-1-api)
- [Luma: Uni-1 start guide](https://lumalabs.ai/learning-hub/luma-uni-1-model)