WHAT’S NEW?
PNG sequence export: Videos can now be exported as individual PNG frames at 1 to 50 fps, making it straightforward to hand off frame-accurate assets to compositing or animation pipelines.
GIF export with frame rate control: Videos can now be exported as GIF files with configurable frame rates from 5 to 50 fps, directly from the export dialog.
Video export in MP4, WebM, and MOV: Videos can now be exported from Layer in multiple formats with codec selection (H.264, H.265, VP9), compression controls, FPS override, and metadata embedding, so deliverables are production-ready without additional transcoding.
Video timeline node fully implemented: The video timeline has been rebuilt as a complete Workflows node with new state management, a sidebar form for controls, and proper slot management, making it stable and composable within automated workflows. Creative Units are now charged for video timeline renders.
Captions in Video Timeline node: Layer now fully supports captions natively.
Text renderer node: A new workflow node for rendering text is now available, enabling text generation to be wired into workflow pipelines on both the frontend and backend.
AI Image reframe in workflows: Image reframing is now available as a workflow node, allowing you to intelligently resize and reposition images as part of automated pipelines.
Prompt node to template conversion: Existing prompt nodes and runtime inputs can now be converted into reusable prompt templates within workflows, making it easier to standardize and reuse prompts across workflows.
Audio tracks for workflow videos: Workflow's video generator node now supports uploading audio tracks for models that support it.
Prompt Template node now generally available: The Prompt Template workflow node is now available to all users with workflow access.
Group-based usage limits: Workspace admins can now create usage groups, assign members to custom Creative Unit quotas, and gate generation when limits are reached, making cost control across large teams more structured.
Workflows Test runs view: Workflow edit and detail pages now include a run history panel showing activity for all generated items, making debugging and output tracking significantly easier.
Public REST API: You can now integrate Layer programmatically using the new public REST API, with endpoints covering workspaces, models, workflows, inferences, and file uploads. Full Swagger documentation, Postman, and Bruno collections are included for immediate developer onboarding. You can refer to the links at the bottom of the side bar on the app.
LATEST MODELS
New models & capabilities were added:
GPT-Image-2, OpenAI’s latest image model is now available in Layer, with support for native output up to 3840px, three quality tiers, stronger text rendering, and masked editing.
Meshy 6, The Meshy 6 3D generation model is now available, offering improved quality and accuracy for 3D asset creation
Grok Imagine 2K resolution, Grok Imagine Image and Grok Imagine Image Edit now support 2K resolution output in addition to the existing 1K option.
BUG FIXES & IMPROVEMENTS
Failed inferences hidden from Activity feed: Failed generations no longer appear in the Activity feed, preventing users from thinking they were charged for unsuccessful runs.
Session delete now instant: Deleting a session now reflects immediately without requiring a page refresh.
MCP error sanitization: Internal error details such as database names and Redis hosts no longer leak to API clients in MCP responses.
MCP rate limiting removed: Rate limiting on MCP workflow execution has been removed, allowing agents and integrations to run workflows in parallel without hitting artificial caps.
GraphQL security hardening: Unauthenticated GraphQL introspection and field suggestions have been disabled in production, and a comprehensive Content Security Policy plus four additional security headers have been added across the app.
HEIC/HEIF files blocked with clear error: Attempting to attach HEIC photos now shows a clear error message instead of silently failing.