Skip to main content
Image model

Luma Uni-1.1 Max

Luma Labs

Released
May 2026
Data date
August 15, 2026
Access
Benchmark configuration
Price
Per image

Luma Uni-1.1 Max combines text-to-image generation through the Agents API with reference guidance, readable typography, and spatially plausible layouts. The Max tier aims to keep products, characters, and visual styles consistent across several iterations.

The API accepts up to nine reference images for generation and up to eight for editing because the source image occupies one slot. Web search can add visual references, and Luma also documents multi-panel output. The model outputs 2K images and uses proprietary weights, so access remains a managed API and web service rather than a local checkpoint.

Position
Rank 5 of 30
Index score
63.8 / 100
1.Krea 2 Large75.6 / 100
2.GPT Image 274.2 / 100
5.Luma Uni-1.1 Max63.8 / 100
6.MAI-Image-2.561.8 / 100
8.Reve 2.160.1 / 100
9.Seedream 5.0 Pro57.2 / 100
11.GPT Image 2.5 Flare56.3 / 100
13.FLUX.2 Max55.8 / 100
14.Nano Banana Pro53.8 / 100
15.Nano Banana 2 Lite53.2 / 100
17.Nano Banana 251.1 / 100
18.FLUX.2 Flex49.4 / 100
19.GPT Image 1.548.3 / 100
20.Qwen Image 2.0 Pro47.7 / 100
21.FLUX.2 Pro46 / 100
23.Ideogram 4.045.4 / 100
25.Seedream 4.037.7 / 100
27.Midjourney V8.128.5 / 100
28.FLUX.2 Klein 9B24.4 / 100
29.HiDream-O1-Image19.3 / 100
Methodology and source

This position gives equal weight to 4 fixed Gradually image tests. One archived first output contributes for each model and task.