Models / Wan / Text to video

Wan text to video prompting guide

How to prompt Wan in text-to-video mode. Every point links its source; community tips are marked. Your agent gets the same guide through the Atlas MCP (get_guide).

Prompt structure

entity→scene→motion→aesthetics→style

• Entity + Scene + Motion; advanced adds aesthetic control (light, shot size, angle, lens, camera move) and stylization. source ↗

Camera vocabulary

• Push-in for intimacy/tension, pull-out to reveal, tracking alongside, orbit (<45°) for importance, fixed for stillness. source ↗

Responds well to

• Voice = line + emotion + tone + speed + timbre + accent; SFX = source + action + ambient; orbit arcs under 45°. source ↗

Duration and limits

• Runway wan3: 2–30 s, 480p/720p/1080p, native audio; video refs ≤15 s total. wan2.7-videoedit input 2–10 s; wan2.2-s2v audio <20 s. source ↗

Multi-shot

• 'Shot 1 [0-3 s] ..., Shot 2 [3-6 s] ...'; on Wan 2.7 'Generate single shot.' forces one shot. source ↗

Avoid and failure modes

• Don't prompt: real people by name, rapid scene changes, exact text legibility, long choreographed action, lip sync to specific words. source ↗

Negative prompt

Supported via .

Real prompts, credited

A breathtaking cinematic sequence showcasing an epic fantasy world. A massive dragon with iridescent scales soars through stormy golden clouds, lightning crackling around its wings. The camera sweeps dramatically from a sweeping aerial shot over a glowing ancient city carved into a mountain cliff, waterfalls cascading into a glowing abyss below. Slow motion embers and sparks drift through the air. Ultra-detailed, volumetric lighting, 8K quality, cinematic color grading.

We are witnessing a massive shift in generative video. Seedance just set the new gold standard. 🚀

Next

Sources

• docs.dev.runwayml.com/api/
• www.alibabacloud.com/help/en/model-studio/text-to-video-prompt