Notes by ReelStack · AI-assistedUpdated 27 September 2026

AI Motion Graphics with Gemini Omni Flash (New)

Embedded text rendering and natural-language shot modifications eliminate traditional motion design timelines and keyframing for rapid title and ad asset iteration.

Video thumbnail: AI Motion Graphics with Gemini Omni Flash (New)
Original YouTube video

Diego Galvao

Published

Watch the original video ↗

What this lesson covers

DGI Kaos demonstrates an end-to-end motion graphics workflow combining Google's Nano Banana 2 Lite for base image generation and Gemini Omni Flash for video animation inside Higgsfield. He highlights how plain-language conversational prompt iteration rebuilds shots with integrated text, realistic environmental physics, and built-in SynthID watermarking at low generation costs.

Key takeaways from the creator

AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.

  1. 01:03 ↗

    Gemini Omni Flash integrates text directly into scenes as physical objects that obey environmental lighting and physics rather than floating overlays.

  2. 01:50 ↗

    Generating a 5-second 16:9 clip in Gemini Omni Flash through Higgsfield costs 15 platform credits.

  3. 03:38 ↗

    Existing video generations can be modified via natural-language text prompts to alter camera speed, color grading, or scene objects in a single pass without timeline masks.

  4. 04:37 ↗

    Video generation with Gemini Omni Flash costs approximately 10 cents per second ($1.00 for 10 seconds), while Nano Banana 2 Lite costs roughly 3.4 cents per 1,000 images.

  5. 05:30 ↗

    Google's SynthID invisible digital watermark is automatically embedded into generated pixels to verify AI provenance.

Workflow outlined in the video

  1. Access the Higgsfield workspace and select Nano Banana 2 Lite to generate base conceptual frames.
  2. Switch to Gemini Omni Flash, configure the aspect ratio (e.g., 16:9), and set duration parameters.
  3. Write a concise motion prompt detailing specific material physics like cloth movement, fluid dynamics, or particle collisions.
  4. Iterate on the generated shot by prompting conversational adjustments for camera pacing, lighting temperature, or object swaps instead of rerolling.
  5. Verify asset authenticity using the baked-in SynthID metadata marker.

Before you use this workflow

These notes describe the source video at its publication date. Model access, pricing, connectors and interfaces may have changed. Check the original source and the provider’s current documentation before installing an add-on, connecting an account or spending credits.

ReelStack has not independently tested this workflow. Preview one representative shot and check motion, continuity and output quality before applying it to a full production. No result, cost saving or model capability is guaranteed.

Explore the tools

How to interpret the numbers

709 views captured 27 September 2026. ReelStack recommendation score: 15/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.

Show the calculation
  • 45% performance: 0.82× views vs 3 other channel videos observed at a similar age. View-evidence factor 41% (views / (views + 1,000))
  • 25% freshness: 4/100 with a 14-day half-life
  • 20% momentum: 4 views/day vs 10 channel baseline (3 comparable uploads), with the same view-evidence factor
  • 10% engagement: 33/100; likes + 4× comments, smoothed with a 500-view neutral prior

Read our methodology and limitations →

Powered by ReelStack

Help keep this running

Your tip funds servers, models, and the time it takes to ship new tools faster. Set any amount below — every bit helps.