Runway MCP prompt generates 30s photoreal stealth-game footage, fully shared
tlakomy · x · 2026-09-15
The author claims "Runway is the future of gaming" and shares a ready-to-reuse Runway MCP prompt that generates 30 seconds of photorealistic 4K third-person stealth-gameplay footage — a countryside petting-farm rabbit enclosure where a farm worker must recover a key snatched by a Dutch rabbit, complete with a simple HUD (objective text, Grab prompt) and controller-style movement.
The prompt structure is the real takeaway: Character locks appearance consistency; Environment details the enclosure, hutches, hay bale and rabbit behavior; HUD constrains UI elements; the story is broken into 0–6s / 6–16s / 16–24s / 24–30s beats; Camera specifies a single over-the-shoulder third-person camera at waist height that lowers on crouch, with smooth tracking and slight lag; Audio enumerates ambience (birdsong, wind, boots, key jingle, UI chimes) and bans music; Rules explicitly exclude teleporting, appearance drift, cartoon style, depth of field, subtitles and watermarks — pre-empting common failure modes.
More from Multimodal
- Google DeepMind on speech-to-speech: conversational, intelligent, multimodal — pick two — AI Engineer · 2026-09-15
- ChatGPT Image Editing Keeps Failing the Simplest Meme Instruction — Imchaman · 2026-09-15
- AI video series lets you dive into Klimt's The Kiss — IamIfOnly · 2026-09-15
- Magehold: A Small AI-Generated Magic Scene with Striking VFX — MosskeepForest · 2026-09-15
- Local Video Gen Start to Finish: What Does Your LTX + ComfyUI Pipeline Look Like? — Normal_Frosting8519 · 2026-09-15
- ACE Step 1.5 Music Generation Now Runs Locally on Android via CPU or OpenCL GPU — sgcego · 2026-09-15