Luma Uni-1

byLuma Labs

Compose multi-character narratives, complex storyboard panels, and authentic manga layouts with physically grounded spatial reasoning

Luma Uni-1

How Luma Uni-1 works

Uni-1 replaces random diffusion noise with an autoregressive planning engine that reasons through spatial hierarchy, reference tags, and lighting physics before generating final imagery.

Draft structured scene directives

Draft structured scene directives

Describe spatial positions, lighting angles, and narrative beats using natural descriptive language or structured Markdown sections.

Link multi-image visual references

Link multi-image visual references

Attach up to eight character, composition, or style references and tag them directly in your prompt text as IMAGE1 through IMAGE8.

Configure style and aspect ratios

Configure style and aspect ratios

Choose between auto rendering and dedicated manga linework across nine native portrait and landscape frames.

What Luma Uni-1 is good at

Explore how autoregressive transformer architecture, eight-slot reference anchoring, and native manga screentone rendering elevate visual storytelling.

Agentic Spatial Scene Planning

Agentic Spatial Scene Planning

Uni-1 calculates internal lighting vectors and spatial geometry before generating pixels, resolving complex multi-subject staging without diffusion noise or spatial collapsing.

Authentic Manga Ink & Screentone

Authentic Manga Ink & Screentone

Switch to dedicated manga mode for traditional ink-and-wash textures, dense screentone shading, and clean linework optimized for vertical panel aspect ratios.

Multi-Reference Visual Anchoring

Multi-Reference Visual Anchoring

Bind up to 8 uploaded reference images by explicitly tagging IMAGE1 through IMAGE8 in your prompt to enforce character features and consistent wardrobe across scenes.

Live Web Context Integration

Live Web Context Integration

Enable web search to pull real-world product blueprints, architectural landmarks, and verified cultural iconography directly into the planning pipeline.

Made with Luma Uni-1

A curated gallery demonstrating physically calculated lighting, complex multi-character staging, and bold editorial palettes created with Uni-1.

Archival reportage with physical light scattering

Archival reportage with physical light scattering

High-contrast commercial luxury product staging

High-contrast commercial luxury product staging

Architectural visualization with calculated ray bounces

Architectural visualization with calculated ray bounces

High-fashion lookbook capture with structured drape

High-fashion lookbook capture with structured drape

Record sleeve design with tactile analog materials

Record sleeve design with tactile analog materials

What people build with Luma Uni-1

From mangakas drafting serialized pages to industrial designers staging luxury prototypes, see how creators leverage agentic image generation.

Manga & Comic Panel Production

01

Generate complete manga pages with authentic screentones, ink linework, and integrated typographic lettering across standard vertical publishing ratios.

Multi-Character Scene Staging

02

Direct intricate multi-figure compositions with physically plausible lighting interactions, spatial depth, and character continuity across sequential frames.

Lookbook & Collection Prototyping

03

Transfer precise fabric textures, garment silhouettes, and model aesthetics across varied environments by feeding up to 8 reference images.

Hardware & Product Visualization

04

Stage complex mechanical assemblies, luxury consumer electronics, and bespoke industrial objects with authentic material refraction and studio lighting.

Brand Campaign Visuals

05

Integrate live web knowledge to produce culturally accurate marketing assets, real-world packaging, and typographic brand banners.

Frequently Asked Questions

Luma Uni-1 uses a decoder-only autoregressive transformer that plans scenes before rendering, rather than denoising random pixel noise like traditional diffusion models. This agentic reasoning phase calculates spatial geometry, lighting vectors, and prompt constraints first, resulting in physically plausible depth, realistic atmospheric scattering, and superior multi-character consistency.

You can upload up to eight reference images and bind them by referencing tags like IMAGE1 (CHARACTER), IMAGE2 (STYLE), or IMAGE3 (COMPOSITION) directly in your text prompt. Explicitly linking the images in your prompt text instructs the model's planning engine exactly how to map character traits, lighting setups, or artistic styles onto the final composition.

Manga mode is a dedicated style preset that generates authentic manga page layouts with clean pen lines, traditional screentones, and integrated typography. It is designed to work natively with portrait aspect ratios (such as 2:3, 9:16, 1:2, and 1:3) to replicate classic Japanese ink-and-wash publication formats.

No, Luma Uni-1 does not support negative prompting. Because it is an autoregressive vision-language model that parses natural instructions, negative keywords like 'no blur' or 'ugly' will be interpreted literally as visual subjects. Instead, describe what you want to see using positive, descriptive natural language or structured Markdown directives.

Enable Web Search when you need accurate depictions of contemporary branding, verified architectural landmarks, real-world products, or historical cultural artifacts. The planning agent consults live web context to verify visual details before rendering, though it is best left disabled for fantasy or abstract scenes to avoid extra generation latency.

Try Luma Uni-1 on Fuser

Compose multi-character narratives, complex storyboard panels, and authentic manga layouts with physically grounded spatial reasoning