# Luma Uni-1 Max AI Image Generator and Editor

> The highest-fidelity Uni-1 tier for polished hero stills and reference-guided edits.

Canonical URL: https://allimageai.com/models/luma-uni-1-max/

Website: All Image AI

Language: English

Luma Uni-1 Max is the highest-fidelity Uni-1 still-image tier. It keeps the same prompt, style and reference workflow as the standard model while prioritising richer detail and stronger prompt adherence for final assets.

## Model details

- Developer: Luma AI
- Status on All Image AI: Active
- Last verified: 2026-08-25
- Maximum output: 1K
- Modes: Text to Image, Image to Image, Edit Image, Multi-reference
- Reference images: up to 4
- Resolutions: 1K
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3

## Best for

- Hero stills
- High-fidelity visual concepts
- Reference-guided finals
- Manga and stylised art

## How to use

1. Choose text generation or upload an image to edit.
2. Identify additional references by order.
3. Pick Auto or Manga.
4. Generate a small batch and compare prompt fidelity.

## Settings explained

### Style

Auto follows the prompt; Manga switches to the model’s documented manga treatment.

### Reference Images

The first image becomes the edit source; any remaining images provide additional visual guidance.

## Prompt examples

### Visual concept

> Quiet futurist library carved into pale stone, warm pools of light, tiny readers for scale, elegant editorial composition

### Reference edit

> Keep the source subject and camera angle unchanged; apply the colour palette and material language of the additional references

## Limitations

- The current operation returns one native image per request
- The interface uses a conservative four-image cap
- Web search is disabled for deterministic generation

## Pricing and credits

Credits for one image at default quality and mode. Resolution, quality, reference inputs, edit mode and output count can change the total. Check the Generate button before submitting.

| Resolution | Credits / image |
| --- | --- |
| 1K | 1 |

Failed generations cost 0 credits. Catalog availability does not guarantee runtime availability; the workspace reports whether the selected model can run.

[Credit plans](https://allimageai.com/pricing.md)

## Test results

Testing in progress. No verified benchmark scores have been published for this model.

## Commercial use and image handling

Commercial use is subject to Luma AI's model and service terms.

Uploads are processed by the configured inference service. You can delete a generation from your history.

## Frequently asked questions

### When should I use Max?

Use Max for the selected final when detail and adherence matter most.

### Does it search the web?

No. The optional upstream web-search field is forced off so generation is deterministic and does not introduce unquoted external context.

## Release history and sources

Date not yet established.

The exact model, checkpoint or provider-specific tier needs to be established before it can be placed on the timeline.

- [lumalabs.ai](https://lumalabs.ai/llm-info)

[Event evidence on the timeline](https://allimageai.com/timeline/#event-luma-uni-1-max)

## Other versions

- [Luma Uni-1](https://allimageai.com/models/luma-uni-1.md): Fast · references