Philipp Schmid Publishes Prompting Guide for Gemini Omni 1.1 Flash Video
_philschmid · x · 2026-08-28
Philipp Schmid published a new prompting guide for Google DeepMind Gemini Omni 1.1 Flash:
- Role binding with tags: use <FIRSTFRAME>/<LASTFRAME> for start/end frames, <IMAGEREF0> as subject/style reference, <VIDEOREF0> (up to 3s) as motion/character reference
- Looping animations: set the exact same image as both first and last frame
- Edit rule: keep edit prompts short and anchor with "Keep everything else the same" to avoid unintended background shifts
- Timecode scripting: choreograph action with bracket syntax, e.g. [0-3s] Person starts walking [3-6s] They stop and look at the camera
More from coding & agent
- Take: context engineering starts at product UX design time, not at build time — andreisavu · 2026-08-28
- Engineering Discussion: Optimizing Context Compaction in DeepSeek Harness — shady101852 · 2026-08-28
- Microsoft Foundry makes Agent Hosting a first-class .NET primitive — adnan_hashmi · 2026-08-28
- Dev Seeks Complex Web App Specs to Stress Test Autonomous Coding Agent — ZenenoDev · 2026-08-28
- Florence launched: AI-ready design system for agents — Scobleizer · 2026-08-28
- AI agents explode issue backlogs, demanding new workflow — rseroter · 2026-08-28