Images · Luma AI
Luma Uni-1
Luma's model that reasons before drawing, good at tricky spatial instructions and styles. Pick it when other models miss the scene.
Anonymized Low costWhat sets it apart
Luma's unified model that reasons before drawing, good at tricky spatial instructions and many art styles including manga. Uni-1 Max costs more than twice as much as the base model.
- Plans the scene before it draws
- Strong on spatial instructions
- Wide range of art styles
Strengths and limits
Where it shines
- Plans the scene: placement, angles, logic
- Wide range of art styles, including manga
Think twice when
- Anonymized, not private: Luma's policy applies
- Max costs more than twice the base model
- Prompts up to 6,000 characters
- About 2.6 credits (Uni-1)
Use cases
A tricky spatial scene
A cat sitting on the left of a bookshelf, a lamp behind it casting a long shadow to the right, a red mug in front of the cat, top-down angle.
It plans placement, angles and logic.
A manga panel
A black and white manga panel of a swordswoman on a rooftop at night, dramatic speed lines, rain.
It handles a wide range of art styles.
Against its rivals
- GPT ImageGPT Image ranks far higher; Luma is chosen for scene logic and style variety.#1 of 37 on Artificial Analysis Text to Image Arena (1,197 Elo)
- Wan 2.7 ImageWan also has a thinking mode and is suited to product shots; Luma leans on spatial reasoning.#29 of 37 on Artificial Analysis Text to Image Arena (990 Elo)
- Nano BananaNano Banana draws on Gemini's world knowledge; Luma on layout reasoning.#4 of 37 on Artificial Analysis Text to Image Arena (1,172 Elo)
Version history
Each version, dated, with what it changed over the one before.
- Luma Uni-1 and Uni-1 MaxLatest
- Unified model for image generation and natural-language editing, opened to developers through the Uni-1.1 API on 2026-05-05
- Max tier scores 1014 versus 992 for the base model on the arena
Benchmarks
How to read these scores: what a benchmark tells you.
Artificial Analysis Text to Image Arena: #22 of 37 models measured in the catalog. Thousands of people compare two images made from the same prompt without knowing the models, and pick the better one. An Elo rating, as in chess: higher is preferred more often. 100 points apart means the higher one wins about 64% of duels.
- 1. GPT Image 2.5 SunburstGPT Image1,197
- 2. GPT Image 2.5 FlareGPT Image1,191
- 3. GPT Image 2GPT Image1,172
- 4. Nano Banana 2.1Nano Banana1,172
- 5. Grok Imagine 2.0Grok Imagine1,155
- 6. Nano Banana 2Nano Banana1,125
- 7. Muse ImageMuse Image1,115
- 8. GPT Image 1.5GPT Image1,107
- 9. Nano Banana ProNano Banana1,102
- 10. Nano Banana 2 LiteNano Banana1,096
- 22. Luma Uni-1 MaxLuma Uni-11,014
- 28. Luma Uni-1Luma Uni-1992
See the numbers
| Model | Elo |
|---|---|
| 1. GPT Image 2.5 Sunburst | 1,197 |
| 2. GPT Image 2.5 Flare | 1,191 |
| 3. GPT Image 2 | 1,172 |
| 4. Nano Banana 2.1 | 1,172 |
| 5. Grok Imagine 2.0 | 1,155 |
| 6. Nano Banana 2 | 1,125 |
| 7. Muse Image | 1,115 |
| 8. GPT Image 1.5 | 1,107 |
| 9. Nano Banana Pro | 1,102 |
| 10. Nano Banana 2 Lite | 1,096 |
| 22. Luma Uni-1 Max | 1,014 |
| 28. Luma Uni-1 | 992 |
All 2 models in this family
| Model | Use | Privacy | Price |
|---|---|---|---|
Luma Uni-1luma-uni-1 | Image | Anonymized | $0.0225 per image |
Luma Uni-1 Maxluma-uni-1-max | Image | Anonymized | $0.054 per image |
Specifications
| Specification | Luma Uni-1 and Max |
|---|---|
| Released | May 2026 |
| Weights | Closed |
| Accepts | text, images |
| Produces | images |
| Price | $0.0225 per image |
| Privacy | Anonymized |
Prices, context and lengths from the live catalog on October 16, 2026; parameters and licenses from the maker.
Sources
Everything on this page comes from these pages, read on October 16, 2026 or as dated on each score.