What's new on Layer

What's new?

• New video models: LTX Video 2.3 & 2.3 Fast. You can now generate text-to-video and image-to-video content using LTX Video 2.3 (enhanced visuals, cleaner audio, portrait support) and LTX Video 2.3 Fast (speed-optimized, up to 20 seconds duration), giving you more flexibility for high-quality video production.

• Live workflow progress tracking: You can now monitor workflow executions in real time directly alongside your tool calls, with step-by-step status updates, cost monitoring, and interactive output previews, so you always know what's running and what it's costing.
• Group image behavior controls: You can now configure whether images in a group are sent as variants or references in the Image Prompt Edit node, giving you more precise control over creative outputs.

• AI-powered prompt generation: You can now use the new Prompt Generator node in blueprints to create many prompts at once with a single instruction prompt so you save a ton of time generated relevant prompts with less manual iteration.

What's next?

• Workspace creative unit transfers: You can now split and allocate creative units across workspaces, with support for auto-transfers from invoices and manual allocation management, making subscription management more flexible for larger teams.
• Browse and inspect models via MCP – Agents can now search and filter available models by modality, type, and capabilities directly through MCP, making it easier to find the right model for your workflow.

What's new?

• New AI models across image and video – You can now generate content using Seedream 5.0 Lite (up to 3K resolution), Nano Banana 2 powered by Gemini 3.1 Flash (1K/2K/4K image generation + editing with batch support), giving you more high-quality generation options across formats.

• Public workflow sharing – You can now share workflows publicly with a single click, so others can discover and duplicate them across workspaces without manual exporting or cloning.

• Refined image & video forms – Image refinement tools (Upscale, Remove Background, Vectorize, Reframe) and video refinement tools (Upscale, Reframe, Remove Background, Add SFX) have been migrated to a new data-driven system, making workflows more scalable and maintainable.

What's new?

• Adjust similarity node in workflows – Fine-tune how closely outputs match reference images for better creative consistency without over-constraining results.
• Improved inference forms in Forge – Run inference with smarter, state-aware forms to streamline complex workflows and reduce reconfiguration.
• Workflows productivity shortcuts – Duplicate nodes using keyboard shortcuts: CMD+D (Mac) or CTRL+D (Windows) for faster workflow building.
• Removed workflow details page – Workflow management has been streamlined by consolidating actions into the editor overview mode and updated workflow cards.

🚀 Export System Improvements (Baseline Release)

A new, unified export experience has been introduced across Layer, providing teams with enhanced control, consistency, and production-ready outputs.

🆕 New Export Dialog (Unified Component)

A standardized export dialog is now used across the platform.

• Quality & Resolution Controls
  • Adjustable output quality
  • Resolution scaling options
  • Consistent behavior across image types
• Admin-Controlled Metadata Toggle
  • Workspace-level setting
  • Admins can enable/disable embedded metadata controlling
  • Applies across all exports within the workspace
• Save Export Preferences Locally
  • Remembers last-used export settings
  • Reduces repetitive configuration for high-volume workflows
• Frontend Alignment
  • All existing download/export entry points now use this unified dialog
  • Consistent behavior across image generation, editing, and workflow outputs

🖼️ Expanded File Format Support

Generated assets can now be exported in:

• PNG
• JPEG
• PSD (NEW)

Embedded Metadata Support

For supported formats, Layer now embeds:

• Model used
• Generation IDs
• Timestamps
• Other internal tracking data

This improves:

• Traceability
• Compliance workflows
• Performance attribution
• Asset lifecycle tracking

PSD Export

• PSD exports include a single generated image as a layer
• Compatible with Photoshop workflows
• Designed for seamless handoff to creative teams

📦 Batch Export via ZIP

• Export multiple assets at once
• Automatically bundle them into a ZIP file
• Maintain metadata and selected export settings across the batch

This significantly improves high-volume production workflows (UA, LiveOps, variants).

What's next?

The following enhancements are planned next:

• Asynchronous Export Notifications — notify users when export processing is complete, especially relevant for large batch exports and Drive upload/download workflows.
• Metadata Preservation Across Uploaded Files — preserve Layer metadata when uploading files into Layer, convert between formats (e.g., PNG → PSD), and ensure metadata continuity across the full asset lifecycle.

Happy January! With the new year comes the GA launch of a brand-new feature: Workflows.

Workflows allows you to automate both simple and complex tasks into just a handful of clicks, giving you the power to generate anywhere from a handful to hundreds of assets at once. Unlike other workflows tool you can parallelize all the runs and save hours of generation time when you're going for large tasks. Want to re-skin dozens of characters at once or an entire game library, or generate dozens of new video variants for your User Acquisition campaigns? Workflows lets you do it! Want to get the most out of Workflows? Check out our tutorial videos on YouTube and help center articles and get creating now.

Features

• Workflows are now available to all users. Simply navigate to the Workflows option on the left nav bar, or pick Workflows from the home page.
• Featured Workflow Templates are available! Featured Workflows have been created by the Layer team and are a great way to start exploring how Workflows can supercharge your UA and Live Ops campaigns or Game Art pipelines. Here are just a few of the things we've built for you:
  • Add an AI hook in front of your UA campaign videos, then automatically export the updated video.
  • Costume your characters in a few simple steps.
  • Use your character images to create TikTok dances, perfect for social sharing.
  • Generate CRM header images at all of your needed resolutions.
  • And much more!
• New templates have arrived. A new Consistent Character Placement template has been added to help you place characters into a diverse range of scenes without sacrificing the character's style. The Style Transfer to Items and Scenes templates have been added as well, and these experimental templates allow you to try out one of the most commonly asked for tools: Taking a few images and applying their visual style to a different image.
• New model organization and tagging is fully live — users can now filter, sort, and organize models in a much better way.

Features

• Kling O1 is here! Take advantage of editing with prompts in your own videos. Upload images and then use the terms @Image1, @Image2, and other numbers to refer to the images. The images you upload are numbered from left to right, top to bottom.
• Hunyuan 3 is here! Take advantage of one of the most advanced 3D models to date and start using this model on Layer.
• Custom Styles are now Custom Models! We've renaming our Custom Styles to Custom Models to better reflect that models may be customized, while styles are reserved for different art styles. We'll be rolling out these wording updates in the coming weeks across the app.
• Veo 3.1 now supports 4 second and 6 second long video in addition to its native 8 second long video lengths.
• New model organization and tagging. Look for an entirely new way of organizing, browsing, filtering and sorting your favorite models, making it easier than ever to find the best model for your job (live by Wed midday).

Features

• Layer Workflows have arrived (in private beta). Gone are the days of creating content 1by1, with Workflows you can now automate your entire content pipeline using an intuitive node-based system.
• Nano Banana Pro is here! We added Google Gemini 3 (AKA Nano Banana Pro) to Layer, including image generation and prompt edit models. The model delivers improved realism and scene composition suited for user acquisition and game assets.
• Even more templates for you to use. Updated template options now leverage Nano Banana Pro capabilities, featuring object removal, isometric conversion, and character element extraction for spine animation workflows.
• Flux 2 arrives in style. The latest image model from Flux is here, ready for you to start using it in your own generations. It complements existing options including Flux 1.1 [pro] Ultra and Flux.1 Dev.

Features

• Sprite Sheet support is now live! Want to bring those pixels to life? We've (finally!) added sprite sheets via our new Templates system. Just select it from the homepage and you're good to go.
• Added new 3D features to match model functionality. Re-topology, higher resolution textures, export formats, and more. We've added a bunch of QoL features to our 3D generations, to match what's available in the market.

Features

• Templates are now live on Layer! You've probably noticed these on our homepage, you can now select preloaded working sessions that make it easier to do specific tasks inside Layer. Anything from TikTok videos to batch upscaling - all available in just a few clicks. We'll be adding lots more of these in the future, give it a try today!