# Luma Uni-1 Canonical page: https://fuser.studio/models/luma-uni-1 Luma Uni-1 in Fuser generates images from text and references, including multi-character scenes, storyboard panels and manga-style page layouts. ## Specs | Spec | Value | | --- | --- | | Inputs | Prompt (text), Reference Images (image) | | Output | image | | Aspect ratios | 3:1, 2:1, 16:9, 3:2, 1:1, 2:3, 9:16, 1:2, 1:3 | | Cost | 58 credits per run | Autoregressive image generation with scene-planning reasoning, multi-reference identity consistency, and dedicated manga styling Creator: Luma AI [Synthesize with scene reasoning](https://app.fuser.studio) ## How Luma Uni-1 works How Luma Uni-1 plans, conditions, and synthesizes structured visual imagery. ### Structure prompt and references Compose your descriptive scene prompt and upload reference images to anchor character identity or artistic style. ### Configure style and web search Choose between auto and manga rendering modes, and toggle web search grounding for real-world factual accuracy. ### Generate reasoned output Receive a structurally coherent image synthesized through autoregressive scene planning and clean boundary definition. ## What Luma Uni-1 is good at Core capabilities spanning autoregressive reasoning, multi-reference conditioning, and specialized comic rendering. ### Agentic Scene Reasoning Uni-1 employs a decoder-only autoregressive transformer to logically plan scene composition, object scale, and spatial relationships before rendering final pixels. ### Multi-Reference Conditioning Ingest multiple reference images simultaneously to preserve character likeness, specific wardrobe textures, and lighting palettes across sequential generations. ### Authentic Manga Engine Switch to dedicated manga mode to synthesize traditional Japanese comic pages featuring crisp G-pen ink linework, dynamic speed lines, and authentic halftone screentones. ### Web Search Grounding Activate built-in web search planning to ground concept art in verified real-world architecture, modern vehicle designs, and cultural artifacts without hallucinated details. ## Made with Luma Uni-1 A visual gallery highlighting structural coherence, authentic manga screentones, and tactile material definition. ### Conceptual poster design with crisp material boundaries ### Cinematic narrative frame with directional underwater illumination ### High-contrast editorial lookbook with vivid chromatic tension ### Tactile archival documentary capture with natural window light ### Serialized manga splash page with authentic halftone screentones ## What people build with Luma Uni-1 From serialized comic production to fact-grounded concept art, explore how creators deploy Uni-1 across production pipelines. ### Sequential Manga and Comic Creation Produce serialized graphic novel pages and comic storyboards with authentic halftone screentones, expressive dynamic ink linework, and rock-solid panel-to-panel narrative pacing. ### Multi-Reference Character Design Lock down facial features, wardrobe details, and signature silhouettes across multiple sequential prompts using reference image conditioning. ### Factually Grounded Concept Art Leverage real-time web search grounding to accurately render real-world industrial products, modern architectures, and cultural artifacts without hallucinated geometry. ### Spatial and Environmental Storyboarding Stage multi-character scene layouts and complex spatial blocking with reasoning-driven compositional depth that avoids diffusion melting and object collision errors. ### Industrial and Hardware Prototyping Synthesize tangible physical concept renders with precise mechanical proportions, authentic surface finishes, and uncompromised material tactile fidelity. ## Frequently Asked Questions ### What is Luma Uni-1 and how does it generate images? Luma Uni-1 is an agentic, reasoning-first text-to-image model developed by Luma AI that uses an autoregressive transformer architecture to plan scenes before generating pixels. Unlike conventional diffusion models that iteratively denoise random noise fields, Uni-1 processes text and visual tokens sequentially. This internal reasoning step enables precise spatial layouts, complex multi-entity relationships, and clean object boundaries without diffusion-style melting. ### What makes the manga style mode unique in Uni-1? The manga style mode renders authentic Japanese comic aesthetics including traditional G-pen ink linework, dynamic cross-hatching, and true monochrome screentones. Selecting the manga style parameter configures the model's visual token generator specifically for sequential comic panels and graphic novel layouts rather than photorealistic textures. ### How does web search grounding work in Luma Uni-1? When web search is enabled, the model actively retrieves real-world reference data during the scene planning phase to ground generation in factual reality. This is particularly effective when prompting for specific modern architectural landmarks, real-world product designs, or contemporary cultural artifacts that require accurate physical and visual details. ### How do reference images work with Uni-1? You can pass multiple reference images into Uni-1 to condition character identity, clothing consistency, or overall artistic style. For optimal results, explicitly define the role of each reference image in your text prompt—such as designating one image for facial likeness and another for compositional lighting. ### What tasks is Luma Uni-1 best suited for, and when should it be avoided? Uni-1 excels at sequential manga and comic panels, multi-image character consistency, complex multi-object spatial compositions, and fact-grounded concept art. Creators should avoid using Uni-1 for sub-second real-time iteration loops or workflows that rely on chaotic, unprompted analog film grain and diffusion noise artifacts. ## Try Luma Uni-1 on Fuser Autoregressive image generation with scene-planning reasoning, multi-reference identity consistency, and dedicated manga styling [Synthesize with scene reasoning](https://app.fuser.studio) ## Related models - [Gemini Image](https://fuser.studio/models/gemini-image.md) - [GPT Image](https://fuser.studio/models/gpt-image.md) - [Seedream](https://fuser.studio/models/seedream.md) - [FLUX.3 Image](https://fuser.studio/models/flux-3-image.md) - [FLUX.2](https://fuser.studio/models/flux-2.md) - [ESRGAN Upscaler](https://fuser.studio/models/esrgan-upscaler.md) Node reference: [Luma Uni-1 docs](https://docs.fuser.studio/docs/nodes/image/luma-uni-1.md) ## More articles - [Luma Ray 3.2 Guide: Prompts, Keyframes, Loops and Reframe](https://fuser.studio/articles/luma-ray-3-2-guide.md)