FLORA Weekly
No. 006,
Saturday Performance Special
Weekend performance boost with significant speed improvements.
🧠 Improved
- Major performance boost - increased viewport node mounting threshold
- In-editor notification polish
FLORA Weekly
No. 005,
Generation Quality Upgrade
Major improvements to generation quality and multiplayer experience, with significant backend optimizations.
📦 New
Editor notifications
for real-time updates and credit returns
Posthog analytics
for download tracking from nodes
- Backend migration for improved performance and reliability
🧠 Improved
- Dramatically reduced bad generations on OpenAI requests - our biggest quality improvement yet
- Gemini model enhancements for better outputs
- Visual redesign of top navigation bars
- Endpoint dropdown with clearer visual hierarchy
- Block titles now auto-populate on connected nodes
🛠 Fixes
- Multiplayer cursor issues resolved - no more seeing your own cursor
- Removed distracting autosave indicator
- Eliminated background node breathing animation
- Credit return notifications now working properly
FLORA Weekly
No. 004,
Universal Styles & Downloads
Introducing universal styles and enhanced download capabilities with improved collaboration features.
📦 New
- Universal Styles - consistent styling across generations
- Download progress notifications with toast alerts
- Left toolbar with hover-activated blocks
🧠 Improved
- Client error dashboard enhancements
- Better flow spawning - nodes no longer overlap
- Comment editing restricted to owner only
- Cleaner UI with removed comment close buttons
🛠 Fixes
- Download functionality on blocks restored
- Clear All button now hidden when no tasks present
- Various UI interaction improvements
FLORA Weekly
No. 003,
Account Flexibility Hotfix
Quick fixes for account management and subscription flexibility.
🧠 Improved
Subscription switching
Seamlessly move between monthly and yearly plans
- Content moderation error messages now display correctly
- Node variations button functionality restored
🛠 Fixes
- Account display issues for inactive users resolved
- Coupon signup flow bugs fixed
- Automatic retry disabled to prevent duplicate generations
FLORA Weekly
No. 002,
Free Tier & Security
Establishing our free tier structure and enhancing account security.
📦 New
500 free credits
for new users to explore FLORA
Hover toolbar
for quick actions
Image upscale
and remove background tools
🔐 Security
- Suspicious activity detection for account protection
🛠 Fixes
- Text context to image node connections fixed
FLORA Weekly
No. 001,
Introducing Ideogram
We’re rolling out Fuse, our new architecture for orchestrating multiple specialized agents in a single workflow. With Fuse, you can now:
- Chain agents with task-specific prompts
- Enable parallel agent execution with shared memory
- Call external tools from within agent trees
The beta includes support for function calling and shared context across agents.
Fuse is available for Pro and Enterprise plans.
📦 New: GPU Auto-Scaling (for Inference APIs)
Our API now supports automatic GPU scaling based on real-time traffic.
This helps reduce cold starts and ensures low-latency inference even during usage spikes.
- Support added for NVIDIA A100, H100
- Billing adjusts dynamically based on load
- Requires no configuration — just deploy your model
🧠 Improved: Model Updates
- Upgraded our default CodeGen-7B endpoint to v2.1 — better accuracy, fewer hallucinations
DocQA model
now supports 150k token contexts
- Improved multi-language support in Chat endpoint (added Korean, Dutch, Polish)
🔐 API Changes
- New
/v1/agents/runendpoint for orchestrated multi-agent flows - Deprecated
/v1/tasks/create— use/v1/agents/launchinstead - API keys can now be scoped per model, feature, or environment (dev/staging/prod)
🧪 Labs
- Internal tests running for speech-to-code pipeline (using Whisper + CodeT5)
- Early access to fine-tuned vision transformer (ViT-x3) for document parsing
- Testing memory-aware agents with local context retention beyond sessions
🛠 Fixes
- Fixed a memory leak in real-time embeddings endpoint
- Resolved an auth issue causing 401 errors on
PUT /models/train - Improved latency for European region (Frankfurt): -35ms avg per call