Luma Agents' Layers Lets Creators Edit Any Image Part Without Rebuilding Everything
Luma Agents adds Layers: extract, isolate, and re-edit any element in an image through natural conversation, powered by Uni-1
- Layers is now live in Luma Agents: extract any image into editable elements and re-edit them through conversation.
- Change one element, preserve everything else — swap products, restyle backgrounds, or rewrite headlines without regenerating the full image.
- Powered by Uni-1, a decoder-only autoregressive transformer that reasons in language and renders in pixels within a single forward pass.
- Works on any image — generated inside Luma or uploaded externally — with no manual masking or selection tools required.
- Targets ad agencies, e-commerce, and localization teams who need to remix the same scene across many variants at scale.
- Available now on Plus ($30/mo), Pro ($90/mo), and Ultra ($300/mo) plans; API access rolling out gradually.
Luma Agents just shipped a feature called Layers that lets you edit one part of an image without touching anything else. You can ask the agent to decompose any image into its constituent elements, then swap the product, restyle the background, or rewrite the headline while the rest of the composition stays locked.
Layers works on any image, whether generated inside Luma or uploaded from outside. The interaction is conversational: describe what you want changed, and the agent handles the rest. No manual masking, no layer panel, no selection tools.
The problem it solves
Anyone who has iterated on a generated image knows the cycle. You get a great product shot, but the background is wrong. You regenerate, and now the product looks different. Standard image generation models treat an image as a single flat output, so changing one region tends to bleed into adjacent areas or force a full regeneration. Traditional background removal tools offer only a binary foreground-background split, which falls well short of what real creative workflows need.
A real ad campaign might require the product, its shadow, the surface, and the background as four independently editable elements. Producing that kind of composite traditionally meant advanced retouching, complex masking, manual shadow reconstruction, and careful color correction, with every additional variant adding production time.
What Layers actually does
The workflow is: generate or upload an image, ask the agent to extract its layers, then iterate on individual elements through conversation. Luma's announcement gives a concrete example of the loop: