GeminiOmni Build Notes

Blog

Read latest product features, solutions, and updates.

AI Image Aspect Ratios: Choose the Right Canvas Before You Generate

AI Image Aspect Ratios: Choose the Right Canvas Before You Generate

A practical guide to 1:1, 4:5, 3:2, 16:9, and 9:16 AI image aspect ratios, composition choices, cropping risks, and multi-format workflows.

Aug 13, 2026
Lena Hoffmann
AI Image Text Rendering: A Practical Prompt and Editing Workflow

AI Image Text Rendering: A Practical Prompt and Editing Workflow

A reliable workflow for generating readable text in AI images, from short copy and layout prompts to iteration, verification, and post-generation repair.

Aug 11, 2026
Lena Hoffmann
How to Reduce AI Video Flicker, Morphing, and Identity Drift

How to Reduce AI Video Flicker, Morphing, and Identity Drift

A systematic troubleshooting guide for AI video flicker, warped subjects, changing faces, unstable backgrounds, and prompt or source-image drift.

Aug 6, 2026
Lena Hoffmann
AI Video Camera Movements: A Prompt Vocabulary With Practical Examples

AI Video Camera Movements: A Prompt Vocabulary With Practical Examples

A field guide to camera movement prompts for AI video, including pans, pushes, trucks, orbits, crane shots, handheld motion, and combinations to avoid.

Aug 4, 2026
Lena Hoffmann

MiniMax H3 Is Live: A Practical Test Checklist for Multimodal Creators

A source-bound checklist for evaluating MiniMax H3 before changing an existing AI video workflow.

Jul 31, 2026
Lena Hoffmann
Image-to-Video Prompt Guide: Describe Motion Without Rewriting the Image

Image-to-Video Prompt Guide: Describe Motion Without Rewriting the Image

Learn how to write image-to-video prompts that preserve the source composition while controlling subject motion, camera movement, timing, and audio.

Jul 30, 2026
Lena Hoffmann
AI Video Storyboard Template: Plan Short Generative Clips Shot by Shot

AI Video Storyboard Template: Plan Short Generative Clips Shot by Shot

A practical AI video storyboard template for turning one idea into coherent shots, prompts, transitions, audio cues, and a repeatable generation plan.

Jul 28, 2026
Lena Hoffmann
How to create images with Gemini — a practical guide for 2026

How to create images with Gemini — a practical guide for 2026

Gemini's image models — Imagen 4 and Nano Banana — turn a text prompt into a finished picture. Here's how text-to-image actually works, the prompt structure that lands, and the fastest free path to your first image.

Jun 29, 2026
Lena Hoffmann
How to make a video with Gemini — a step-by-step guide for 2026

How to make a video with Gemini — a step-by-step guide for 2026

Gemini doesn't render video itself — Veo does, and you reach it through Gemini. Here's exactly how text-to-video works, the prompt structure that actually lands, and the fastest free path to your first clip.

Jun 11, 2026
Lena Hoffmann
What we know about Gemini Omni 48 hours before Google I/O

What we know about Gemini Omni 48 hours before Google I/O

Strings in the Gemini app, a 9to5Google leak, and what Veo 3.1 already does — together these draw a fairly clear picture of what Google is about to announce. Here's my read with seven days to go.

May 12, 2026
Lena Hoffmann
My Google I/O 2026 keynote watch list — what indie builders should actually listen for

My Google I/O 2026 keynote watch list — what indie builders should actually listen for

Most of the I/O coverage will focus on consumer features and stock price impact. Here's what indie AI builders should actually be tracking when Sundar walks onstage on May 19 — the seven specific signals that change what's worth building this summer.

May 11, 2026
Lena Hoffmann
Why Veo 3.1 Fast beats Sora for indie video work — published per-call costs

Why Veo 3.1 Fast beats Sora for indie video work — published per-call costs

After two weeks of side-by-side generations, I'm convinced Veo 3.1 Fast is the right default for indie video work. The reason isn't quality. It's that Google publishes a per-second price and OpenAI buries Sora behind a $200/month bundle.

May 10, 2026
Lena Hoffmann
Gemini Live is the most underrated thing Google shipped in 2026

Gemini Live is the most underrated thing Google shipped in 2026

Real-time voice with Gemini at $0 on the Free tier. Everyone's busy waiting for Omni; the model that actually lets you build a Pixar-style voice assistant has been hiding in plain sight since April.

May 9, 2026
Lena Hoffmann
Nano Banana 2 vs Imagen 4 — when to pick which (and why I ship both)

Nano Banana 2 vs Imagen 4 — when to pick which (and why I ship both)

Both are Google. Both are 2026 flagships. They do different jobs. Here's the decision tree I use, with the actual prompts and pricing that prove the point.

May 8, 2026
Lena Hoffmann
1M token context isn't free — the real per-page cost of Gemini PDF chat

1M token context isn't free — the real per-page cost of Gemini PDF chat

The 1M-token context window sounds magical until you do the multiplication. Here's what a 1,500-page PDF actually costs to chat with on Gemini 2.5 Flash — and the price logic behind GeminiOmni's free-under-200-pages tier.

May 6, 2026
Lena Hoffmann
Why your AI tool should never have a Gemini key in the browser — a server-side proxy walkthrough

Why your AI tool should never have a Gemini key in the browser — a server-side proxy walkthrough

The pattern that saves indie AI builders from $5,000 surprise bills. A full walkthrough of the server-side proxy GeminiOmni runs in front of every Gemini API call, with the actual code patterns and edge cases.

May 4, 2026
Lena Hoffmann
The first thing that broke when I shipped GeminiOmni

The first thing that broke when I shipped GeminiOmni

Twenty-three minutes after I made the site public, the Gemini API key in the browser was being scraped. Here's exactly what happened, what it cost me, and the architecture change I shipped that afternoon.

Apr 29, 2026
Lena Hoffmann