Export to Drive, Spellcheck & Inpainting Overhaul

Usage-based plans are here.

Five new prebuilt actions: QR Code Generator, Generate Text Image, Add Text to Image, Generate Shape Image, and Add Shape to Image.

Pro plan users can now create and use custom voice profiles from ElevenLabs in audio generation workflows.

A new full-screen intro modal guides first-time builders through the technique creation flow.

The node picker has a new layout with both list and grid views, plus tooltips that describe what each node does.

Techniques can now be starred as favorites directly from the library picker.

Rerun individual cells directly from the masonry grid view without switching context.

Pasting nodes now duplicates full generation history, so you keep your creative trail intact.

Fit/fill toggle for thumbnails, test-run errors visible in the workflow overlay, and test-run results on the Status tab.

Targeted node and edge selectors, optimized hover animations, throttled text-block resize, and faster connection line rendering for smoother editing on large canvases.

Smoother progress indicator and loading state that now survives page refresh.

Drop and replace support for audio nodes, audio playback stays alive across generation switches, and downloads preserve the correct file extension.

Forward seed values to Nano Banana for deterministic, reproducible generations.

Pro and Max plans now include unmetered generations on Nano Banana models with higher rate limits (225/hour).

Easily share your creations with the world with our new node sharing feature in the toolbar! Get a simple media link you can share.

parameter editing — multi-select any group of generation nodes that share parameters and edit them together.

rerun single cell — re-run one variation without rebuilding the batch.

The next generation of actions is now live in the action library:

Grab every output from a session in one click

Techniques — category chips appear in the canvas popover and the My Techniques tab, and the list sorts by last updated - so the technique you were just iterating on is always on top.

upstream connectors in Technique Builder — click any output in the technique builder and its upstream chain lights up, making complex graphs much easier to read.

Pinned labels now stay attached to their target across nested groups

More reliable token-by-token rendering in Text Nodes

now work with GPT image endpoints

Upload assets directly from your Google Drive into any FLORA project.

Actions (code nodes) now work inside Techniques.

Teach FAUNA custom skills tailored to your workflow.

FAUNA can now discover, place, and execute prebuilt Actions on the canvas autonomously.

Opus 4.7, Opus 4.6 Fast, GPT 5.5, and GPT 5.5 Fast are now available.

Document nodes now support target-aware outputs, a fullscreen editing mode, and thumbnail previews, making them much more useful for text-heavy workflows.

Kling Pro video models now route to the 4K endpoint when you select 4K resolution, delivering cinema-quality output.

Two new model training options for fine-tuning custom models.

Upload images in Apple's native formats directly.

Reference other nodes with @ when editing technique descriptions, bringing the same wiring convenience from prompts into the builder.

A new success dialog after publishing shows app link share controls, making it easier to share your techniques with the community.

A new toggle lets you add prefix and suffix text around each part individually, useful for structured prompt assembly.

Magnet handles and edge updates now bypass React for significantly smoother dragging and connecting on large canvases.

Action node workflows consolidated from 12 steps to 3 on the happy path, making code-based nodes noticeably faster.

End-of-turn processing cut from ~10 steps to 2, so FAUNA finishes its work and hands back control faster.

Chain two batches into a grid of every combination, laid out visually for side-by-side comparison.

Reframe any image from a new perspective with a full 3D angle control.

Drop resizable text notes anywhere on the canvas with Shift + A Perfect for labeling sections, leaving comments for collaborators, or organizing complex workflows.

Google's Gemini text-to-speech is available on audio nodes.

A Tutorials section in the Community tab with guided project templates.

The quick upscale action now uses Topaz for sharper, higher-fidelity results.

The canvas now remembers your zoom and pan for every project.

Drag, zoom, bulk-connect, and selection have been rewritten so large projects feel dramatically smoother.

Errors now render as a banner directly on the block that failed, with a header indicator and an expandable task bar so you can scan every error across a project at once.

in Prompts — type @ anywhere in a prompt box to reference another node on your canvas.

Generate — a standalone generate flow built for phones, with full-screen model picker, mode switcher, client-side credit checks, and a 4-image default (everything tuned for thumbs).

Color Tagging — tag blocks with colors, filter the canvas with glow and border highlights, and bulk-download everything sharing a tag.

& Parameter Badges in FAUNA chat — see at a glance what's running on each response.

2.0 Fast video models available on the model picker.

Builder graduated from beta — available to everyone now, with a new onboarding video and smoother exit confirmation

reliability — Gemini rate-limit errors fail fast instead of retrying; fallback routing adapts in real time

Run Counts — see how often a technique has been used, right in the library.

Member Role Editing — admins can edit member roles directly from the workspace settings.

discoverability — richer structured data on public technique pages.

Nodes — a dedicated audio node with waveform playback, voice selector, ElevenLabs text-to-speech and speech-to-text, Gemini audio inputs, and automatic routing that picks the right model for music, speech, or sound effects.

Editor Rewrite — new stencil masking, shapes, text rotation, multi-select resize/rotate, drag-to-adjust numeric inputs (hold and drag any number field), and a proper empty state.

Picker in Add-Node Menu — search techniques with hover-preview thumbnails right from the canvas.

+ \ — Keyboard shortcut to toggle all canvas toolbars to maximize your workspace.

grouping in generation history — variants from the same batch are grouped and highlighted together in the carousel.

chat — roughly 3× faster to first token

FAUNA sessions — now compact automatically, so conversations stay responsive over time

Reusable visual references (characters, styles, color palettes) that live as nodes on your canvas.

Reference any canvas node directly from a prompt field.

Find and add any model instantly.

Browse every generation you've ever made.

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.

Connect a batch node to a full multi-step workflow and run everything end-to-end.

Use powerful pre-built workflows directly in your canvas or run them independently.

Now available for all users in the Layer Editor.

Keep your canvas clean with a simple routing node.

Click any collection item in the batch node and it automatically selects the corresponding generation in the downstream node. No more hunting through outputs.

Use text delimiting or upload a CSV directly to power your batch runs, making it much easier to process structured inputs at scale.

New dropdown in the Layer Editor with your most-used formats baked in. Pick your ratio and keep moving.

A full compositing toolkit for combining multiple images into layered compositions, right on your canvas.

Process multiple assets through a single generation in one run.

The auto-model toggle is now labeled "Auto select mode" for clarity, and defaults to on.

Google's Gemini 2.5 Flash Image model is now the default for image generation.

New preference in Account Settings to show or hide your remaining credit balance in the credits indicator. Your workspace, your rules.

Unpack a node's full generation history into individual nodes.

Download all generations from a node as a single ZIP.

One click in the toolbar to expand the display dimensions of a text node.

updates

Prevent accidental edits to finalized layers.

Pixel-perfect placement with arrow keys.

Layers now snap to frame edges and center points during resize, with snapping enabled by default.

Additional aspect ratio options in the Layer Editor.

Cleaner, more visible frame border in the Layer Editor for easier spatial orientation while compositing.

Reorganized and streamlined with tooltips on every action, so you spend less time hunting for controls.

Tab and Shift+Tab now cycle through dimension inputs in the properties panel, committing values as you go. Faster than clicking between fields.