What Is The New Luma app?
Your creative collaborator and the most capable multimodal Agent, built to collaborate with you to execute professional creative work end-to-end, from brief through delivery through different layers of execution
It allows you to:
Generate text, images, video, audio, and voice across the world’s leading models while maintaining shared project context
Transform and evolve existing media across formats without restarting work or rebuilding assets
Organize initiatives on boards where agents generate, iterate, and evolve assets across the project
Collaborate in real time with teammates, external partners, and agents operating in parallel
Direct production through natural language or direct controls while agents coordinate models and execute tasks across the workflow
Instead of switching between tools, timelines, generators, and editors — Luma unifies them into a single visual workspace powered by AI agent collaborators there to support you, execute creative tasks, and help you understand how to do it according to your own vision and proficiency level.
Think of it as a highly skilled teammate that you can collaborate with in a super fast, prolific feedback loop with unmatched speed, scale and creative fun.
How Luma Works
Luma advances creative work through agents that execute projects from brief through final delivery while maintaining shared context across every stage. Work is organized on boards where agents generate, iterate, and evolve assets across the initiative.
The Three Core Layers
Project Organization
Boards organize creative initiatives visually so teams can structure scenes, concepts, references, and production assets in one place
Assets, versions, and explorations can be grouped and compared while preserving project context
Teams collaborate in real time with agents advancing work alongside them
Semantic search instantly locates assets, references, and iterations across the project
Work evolves spatially across boards rather than through folders or disconnected timelines
Creative Agents
Luma's Creative agents execute and advance professional creative work across the entire process while maintaining shared project context.
You:
• Direct creative work through natural language
• Request iterations, refinements, and alternative directions
• Gather references, research, and inspiration within the project
• Evaluate outputs and guide quality improvements
Agents:
• Route tasks across Luma models and industry-leading models automatically
• Generate text, image, video, and audio assets
• Iterate and evolve assets while maintaining shared context across the project
• Evaluate outputs and advance work toward final delivery.
Capabilities
Creative agents access and orchestrate Luma's models and other industry-leading models to execute creative work across all modalities while maintaining shared project context. Agents route tasks across advanced video models including Ray3.14, Veo 3.1, Sora 2, and Kling 3.0, and specialized image models including Luma Omni, Nano Banana, Seedream, and GPT Image
Image
• Photorealistic generation
• Stylized illustration
• Concept art and visual exploration
• High-fidelity editing and enhancement
• Outpainting and reframing
Video
• Text-to-video generation
• Image-to-video animation
• Video transformation and modification
• Keyframe interpolation
• Video extension and scene continuation
• Character-consistent generation
Audio
• Sound effects generation
• Music generation
• Voiceovers with emotional control
• Word-level transcription
Lip Sync
• Audio-to-mouth synchronization
• Expression control
• Character animation
Composition
• Programmatic editing of video and motion elements
• Captions, transitions, and compositing
Agents automatically route tasks across the appropriate models while preserving context across the project. Advanced users can also access individual models through the board UI when manual control is preferred