Wan video to video prompting guide
Last checked 2026-10-11Wan 2.x / 3.0 (Alibaba) · Wan 2.5 Preview (t2v), Wan 2.6/2.7/3.0
How to prompt Wan in video-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
edit instruction→ref image job→what to keep
- Entity + Scene + Motion; advanced adds aesthetic control (light, shot size, angle, lens, camera move) and stylization. source ↗
What the text should describe
- Instruction-only: media = the video, prompt = the edit ('Convert the entire scene to a claymation style'). With refs: add up to 4 reference_image items and name the transfer ('Make the horse-headed character in the video wear the striped sweater from the image'). source ↗
- For continuation use Wan 2.7 image-to-video, not the editor. 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
Convert the entire scene to a claymation style
Next
All Wan modesWan model, prices & shotsFrom $0.05/s · pricesSeedance video to videoKling video to videoRunway video to videoLuma video to video