## Elements, @ Mentions, & More  
### Mar 27, 2026  
### ・  
### 2.15  
This release introduces Elements — reusable visual references that live right on your canvas — alongside @ mentions for wiring nodes together, a searchable model menu, full generation history on your dashboard, and major upgrades to batch workflows.  
📦 **New**  
- **Elements** — reusable visual references (characters, styles, color palettes) that live as nodes on your canvas. Create them from a right-click or from any selection of existing generations, then pull them into any prompt by typing `#`. A picker appears, the element's images are automatically fed as input, and the system warns you if you exceed a model's max input count. Learn more about Elements and model compatibility [here](https://docs.flora.ai/editor/elements).  
- **@ Mentions** — reference any canvas node directly from a prompt field. Within any prompt field, type `@` to open a picker of compatible nodes (connected ones grouped at the top), select one, and a graph edge is created automatically — feeding that node's output into your generation. Works alongside `#` for elements, giving you two fast ways to wire context into prompts.  
- **Add Node Menu — Model Search** — find and add any model instantly. The Add Node menu now includes a search bar across every available model, grouped by provider with submenu expansion. Type to filter, set a quantity for bulk-adding, and models are automatically filtered by compatibility with your current connections.  
- **Dashboard — Generation History** — browse every generation you've ever made. A new masonry-grid page on the dashboard shows all past generations across every project with infinite scroll and export options — perfect for revisiting earlier work or pulling assets into new projects.  
🧠 **Improved**  
- **Batch Node — click-to-select sync** — clicking a collection item in a batch node now auto-highlights the matching generation in downstream blocks, making it easy to trace results through complex workflows.  
- **Batch Node — downstream workflows** — connect a batch node to a full multi-step workflow and run everything end-to-end. Each item flows through all downstream blocks automatically, unlocking true pipeline-style batch processing.