Create

Stable Diffusion 3.5 Models Optimized with TensorRT Deliver 2X Faster Performance and 40% Less Memory on NVIDIA RTX GPUs

In collaboration with NVIDIA, we've optimized the SD3.5 family of models using TensorRT and FP8, improving generation speed and reducing VRAM requirements on su…

Welcoming Payload to the Figma team

7 moments that shaped Figma, as told by Dylan Field

Supporting faster file load times with memory optimizations in Rust

In good company: How agencies are transforming client collaboration

Canvas, meet code: Building Figma’s code layers

6 skills every engineer needs for the AI era

The FLUX.1 Kontext hackathon

We hosted a hackathon with BFL for FLUX.1 Kontext. Here were the winners.…

Figma Files Registration Statement for Proposed Initial Public Offering

Rolling out Santa without freezing productivity: Tips from securing Figma’s fleet

How we shaped the visual identity for Config 2025

Compare AI video models

It's hard keeping up with every new video model. In this post we'll help you pick the best one for your needs.…

In good company: How retailers use Figma to elevate e-commerce

How we optimized FLUX.1 Kontext [dev]

A deep-dive into the Taylor Seer optimization technique…

Bria is now on Replicate

We've partnered with Bria to bring a suite of commercial-grade image generation and editing models to Replicate. Built entirely on licensed data, Bria’s tools a…

Generate consistent characters

We compare the best image models for generating consistent characters from a single reference image.…

Figma deepens roots in Australia with local data hosting and more

Mike Krieger and Luis von Ahn join Figma’s Board of Directors

Prompt, prototype, perfect: Figma Make is now available to all users

The making of a product icon

Figma Announces Increase in Initial Public Offering Price Range

A tale of two parameter architectures—and how we unified them

Figma Announces Pricing of Initial Public Offering

Open source video is back

Wan 2.2 is our fastest, cheapest video model.…

How to prompt Veo 3 with images

You'll be surprised what you can do with AI video now.…

The Duolingo method: Collaboration as a core practice

Stability AI Achieves SOC 2 Type II and SOC 3 Compliance, Reaching New Industry Standard for Enterprise-Grade Security

Stability AI has achieved SOC 2 Type II and SOC 3 compliance, which validates our security controls and data protection practices through rigorous third-party a…

Introducing Stability AI Solutions: Generative AI Solutions to Accelerate Enterprise Creative Production

Today we’re introducing Stability AI Solutions, a new offering designed to help enterprises scale creative production with generative AI.…

Design systems and AI: Why MCP servers are the unlock

Getting into the groove: How music shaped the scatter brushes in Figma Draw