This update makes it faster to work with video and build workflows, plus adds two powerful new AI models. Extract key frames from any video on your canvas, create connected nodes with a single keystroke, and generate with Kling 3.0 and OpenAI o3.

📦 New

• Video Frame Extraction — right-click any video to extract its first or last frame as a standalone image. Perfect for pulling start and end frames to use as references, style guides, or inputs for image-to-video generations without leaving your workflow.

• Kling 3.0 — Kuaishou's unified multimodal video model with native audio generation and up to 15-second clips. A major leap in cinematic AI video: improved character consistency, multi-shot storyboarding, synchronized dialogue across multiple languages, and significantly cleaner motion in fast-paced scenes. Ideal for narrative-driven video workflows.

🧠 Improved

• Keyboard shortcuts for node creation — press T (text), I (image), or V (video) with any node selected to instantly create a new connected node of that type, dramatically speeding up workflow building.

This release is all about reducing friction before you hit Run. You'll now see upfront credit estimates on every generation, start with stronger default models out of the box, and experience fewer timeouts on long-running jobs. Small changes that add up to a smoother, more predictable workflow.

🧠 Improved

• Credit Estimates on Generate & Bulk Runs — see exactly what a job will cost before you commit. The Run button now displays a clear credit estimate tooltip upfront, with visual warnings when costs exceed your remaining balance. No more surprise failures mid-batch or guesswork when scaling up expensive workflows.

• Stronger Default Models — better results from your very first generation. Image generation now defaults to Flux 2, video and image-to-video default to Seedance 1.5, and inpainting uses Nano Banana Pro.

• More Reliable Long-Running Generations — fewer timeouts, steadier progress. Extended jobs that previously timed out due to progress streaming issues should now complete more consistently. We've stabilized progress updates and increased underlying timeouts under the hood, which means fewer interrupted workflows and less need to retry. You'll notice this one when you don't notice it—your heavy jobs just finish.

FLORA's biggest pricing evolution is here. We're eliminating per-seat pricing entirely—your whole team now shares a single credit pool with unlimited members.

📦 New

• Credit-Pooled Plans - purchase credits, not seats, and invite your entire team. Share a flexible credit pool across unlimited team members without paying per person. Perfect for growing teams, agencies, and organizations where headcount fluctuates.

• Volume Discounts - better rates as your credit needs grow. Scale plan (250K credits) offers significant savings, with additional discounts available on annual billing.

🧠 Improved

• All AI models now available on every plan - no more gated access by tier

• Downloads, exports, and all features unlocked - previously gated capabilities are now accessible to everyone

• Annual billing savings - save up to 17% with yearly commitments across all plans

🔐 Billing Changes

• Existing subscribers are automatically grandfathered at current rates indefinitely

• No forced migrations or automatic upgrades will occur

• Plan modifications are a one-way door—switching to new pricing is permanent

📚 Learn more about usage-based pricing →

Edit Where You Generate

This release makes FLORA a complete image creation environment—generate, then perfect without ever leaving the canvas. Split compositions into layers, paint in or out to refine and extend, and crop to focus. Plus, the editor has more indicators to keep you in flow: keyboard shortcuts surface naturally through tooltips, and essential asset context is always visible.

📦 New

• Inpainting — replace or remove elements directly on the canvas. Select any region and regenerate just that area. Swap out objects, fix artifacts, or erase distractions without starting over.

• Outpainting — extend your images beyond the original frame. Expand the canvas in any direction and let AI fill in the new space. Great for adjusting aspect ratios or giving compositions more room to breathe.

• Cropping — narrow in on what matters. Focus your image to the exact frame you need, right where you generated it.

• Split into Layers — turn one generation into editable pieces using Qwen's layered edit model. Separate foreground, background, and objects into individual outputs so you can iterate on parts of your composition without regenerating everything. Perfect for refining hero elements while preserving what already works.

To learn more about inpainting and outpainting, visit FLORA Docs.

🤖 New Models

• Gemini 3 Flash — Google's latest speed-optimized model. Another option in the speed/quality tradeoff, ideal for rapid iteration when you want faster feedback loops without changing the rest of your workflow.

🧠 Improved

• Keyboard shortcuts in tooltips — hover over any toolbar item to discover its shortcut. Power users move faster, and new users learn speed paths naturally while they work.

• Info panel visible by default — resolution, cost, model, and other context now shows without hunting. Learn more about the underlying media assets you're working with, at a glance.

• Folder labels on dashboard projects — quickly see which folder each project belongs to