Fibo 2.0 is live: the #1 open-weights image editing model on @ArtificialAnlys. Ahead of 33 closed models from leading labs, and trained only on licensed data. Try it in Bria Create: https://t.co/ytQ
The Hook
“(No spoken dialogue — energetic electronic track with vocal chops)”
Feature Teaser
“(No spoken dialogue — rhythmic beat continues)”
Feature Teaser
“(No spoken dialogue — upbeat rhythm)”
Product Reveal
“(No spoken dialogue — bass synth build-up)”
Call to Action
“(No spoken dialogue — rhythmic outro)”
Synthesizable in Remotion · key components of the bria-fibo-launch-grid template.
Dynamic white coordinate grid lines with dot nodes that pulse and frame focal subjects.
Render SVG line and circle elements mapped to viewport percentages, animating strokeDashoffset and opacity via spring().
Central bounding cell blurs and swaps nested asset variations while outer framing stays static.
Use CSS clipPath and interpolate() to flash blur filters between alternating image frames on key beats.
Mosaic grid blocks slide in synchronously, framing copy and image tiles before centering the logo.
CSS Grid layout with cells animating width, height, and transform translate based on current frame.
Purpose. Demonstrate wide commercial applicability across active and lifestyle scenes.
Execution. Rapid cuts with grid overlays and blur-in effects.
Purpose. Highlight precise AI-driven modification capabilities.
Execution. Subject remains fixed while sunglass models swap seamlessly.
Purpose. Reassure enterprise users regarding photorealism and detail.
Execution. High-detail macro portraits and textures.
Purpose. Introduce FIBO 2.0 and direct users to convert.
Execution. Geometric grid formation resolving to BRIA logo and availability.
Objective
E-commerce AI Virtual Try-On LaunchHow the recipe adapts
Applies the targeting grid to apparel swaps on fashion models, shifting between jacket styles while keeping pose and background identical.Scene durations (5 scenes, 24s)
Key Remotion components
Introducing Griffin, the first AI to pass the video Turing test
The most emotive and controllable TTS model
We just released QVAC TranscribePsy, a speech-to-text model small enough to run inside a phone app. It covers 25 European languages on a laptop and 8 on a phone, and on an iPhone 17 Pro Max's Ne