Gemini Veo 3 Photo‑to‑Video Feature

Łukasz Grochal

Google has introduced a groundbreaking photo‑to‑video capability in its Gemini AI, powered by the Veo 3 model. Subscribers to Google AI Pro and Ultra can upload any photo, write a prompt describing desired motion and sound, and generate an 8‑second, 720p video clip complete with synced audio—everything created automatically . This feature is available via the Gemini web app, mobile (iOS/Android), and the Flow filmmaking tool, in over 150 countries—though initially free trials are limited to Pro subscribers.

Generated videos include visible AI‑watermarks and hidden SynthID tags to ensure authenticity. Google reports over 40 million Veo 3 videos have been produced since May, highlighting rapid adoption. While reminiscent of other AI video tools, Veo 3 stands out for its realism, audio integration, and ease-of-use, signaling a major leap in AI-powered creative tools.

References
3 sources
01
blog.googlegoogle.blog
02
gemini.googlegemini.google
03
techradar.comTech Radar
DeepSeek V4‑Pro 1.6T‑Parameter AI Model Architecture

DeepSeek V4: 1M‑Token Context and Budget Frontier AI Models

Palantir Manifesto Graphic: AI Defense and Culture Clash

Palantir Manifesto Hits at Regressive Cultures and AI Shift

OpenAI ChatGPT Images 2.0 feature overview

OpenAI Updates ChatGPT Images With Better Text

Publishers Are Shutting Out Internet Archive

News Giants Block Wayback Machine Over AI Fears

Claude Design Launch: Brand-Aware AI Prototyping Image

Anthropic Launches Claude Design to Rival Figma Tools

Qwen3.6 Coding Agent Benchmarks Chart Visual

Exploring Qwen3.6: Coding Benchmarks and Speed

Palantier Dilemma Human Rights vs Sercurity

Europe's Palantir Boom Amid Sovereignty and Rights Fears

Project Glasswing: Anthropic Mythos Zero-Day Exploit Finder Art

Claude Mythos Leak Ignites Fears of Unstoppable AI Exploits

OpenRouter LLM Leaderboard April

Chinese AI Models Dominate OpenRouter Top Six in Token Usage

Claude Code’s Big npm Leak

Inside the Claude Code Leak and Anthropic’s Agent Design