What Is Luma Uni-1?
Luma Uni-1 is a unified still-image model that can generate from text, use visual references and edit a source image. Web search is deliberately disabled so a run depends only on the prompt and uploaded images.
Luma Uni Model Versions
Luma Uni-1
Fast · references
From 1 Credits
Luma Uni-1 Max
The highest-fidelity Uni-1 tier for polished hero stills and reference-guided edits.
- Resolutions: 1K
- Reference images: up to 4
- Modes: Text to Image, Image to Image, Edit Image, Multi-reference
- Speed: Balanced
Luma Uni-1
A remarkably low-cost unified model for generation, reference guidance and natural-language edits.
- Resolutions: 1K
- Reference images: up to 4
- Modes: Text to Image, Image to Image, Edit Image, Multi-reference
- Speed: Fast
What Is Luma Uni-1 Best For?
- Fast visual exploration
- Low-cost edits
- Reference-guided generation
- Manga concepts
How to Use Luma Uni-1
- Choose text generation or upload an image to edit.
- Identify additional references by order.
- Pick Auto or Manga.
- Generate a small batch and compare prompt fidelity.
Luma Uni-1 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.
The panel above shows only the parameters Luma Uni-1 actually supports. Switch versions and unsupported controls disappear rather than sitting there doing nothing.
Luma Uni-1 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
Luma Uni-1 Test Results
Testing in progress
Every model runs the same eight-category prompt set — portrait, product, poster text, anime character, interior, multi-reference, image editing and character consistency — recording generation time, success rate, text accuracy and identity retention. That run has not finished for Luma Uni-1, so this page shows no scores. We do not publish numbers we have not measured.
Luma Uni-1 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
Luma Uni-1 Pricing and Credits
Credits scale with resolution and image count. The Generate button always shows what this run costs.
1K
1 credits / image
Failed generations cost 0 credits.
Commercial Use and Image Rights
Commercial use is subject to Luma AI's model and service terms.
- Model used: Luma Uni-1
- Model developer: Luma AI
- The inference route is managed internally and may change without changing the selected model
- Uploads are sent only to the configured inference service needed to complete the generation
- You can delete any generation from your history at any time
Frequently Asked Questions
When should I use the standard tier?+
Use the standard tier for inexpensive iteration and everyday edits.
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.
Model Updates and Changelog
- 2026-08-25 —— Luma Uni-1 added with exact generation and edit companions.
Related Models and Tools
AI Image Generator
One prompt box, every major model. Describe it, pick a model, generate.
AI Image Editor
Upload an image, describe the change. Only the part you named moves.
Image to Image
Start from an image. You decide how much of it survives.
Luma Photon Flash
Text To Image · Image To Image · Image Editing
Photon 2
Text To Image · Image To Image
Nano Banana 2 Lite
Text To Image · Image To Image · Image Editing
Nano Banana 2
Text To Image · Image To Image · Image Editing