FLORA adds Google's Gemini Omni Flash video model to its canvas
By Steven Van ·
The video model edits clips through conversation and renders legible on-screen text, live now on FLORA's node-based workspace.
FLORA has switched on Google's Gemini Omni Flash, bringing Google's next-generation video model directly into its infinite creative canvas. Announced by the FLORA team on June 30, 2026, the integration lets designers and brand teams generate and refine video alongside their text and image work in a single node-based workspace, powered by Google Cloud.
What Gemini Omni Flash brings to the canvas
Gemini Omni Flash is the first model in Google DeepMind's new "Omni" family. It accepts text, image, audio, and video as input and outputs high-resolution video that you edit through conversation rather than re-prompting from scratch. It excels across text-to-video, image-to-video, reference-to-video, and video editing tasks, and it renders legible on-screen text and kinetic typography synchronized to movement, useful for product labels, pricing, and call-to-action overlays baked straight into the footage. Google opened developer access through the Gemini API and AI Studio the same day it landed on FLORA. You can pair it with Gemini for reference prompts and storyboarding.
Conversational editing instead of re-generating
The standout capability is conversational editing. Instead of exporting frames, opening a separate editor, or regenerating a clip from zero, you treat the video as a living artifact and issue natural-language instructions that the model applies as iterative refinements. On FLORA's canvas, that means a generated clip becomes another node you can connect, branch, and revise without ever leaving the workspace, keeping the whole creative flow in one place.
Why it matters for creative teams
FLORA already unifies 50-plus text, image, and video models, from FLUX Pro to Google's Veo 3, on one node-based canvas used by teams at Pentagram and Lionsgate. Adding Gemini Omni Flash gives those teams capabilities that were not commercially viable before, from virtual garment replacement to cinematic product hero shots to kinetic typography at scale, all with the reliability of Google Cloud behind the compute. For studios iterating fast on brand-consistent output, having a state-of-the-art video model native to the same canvas as ideation and editing removes a real bottleneck.
Sources: FLORA (florafauna.ai), Google DeepMind — Gemini Omni, Google Cloud — Gemini Omni Flash.