How should I phrase motion in text prompts for Kling-style models (visible cues) and what does Hailuo's 'one major motion per clip' guidance claim about ghosting?
Problem. Text-only motion prompts give vague or ghosted movement. Conditions. I2V/T2V prompts of 4-15 s clips. Vendor statements. Kling's guide: motion prompts work best when they describe what the viewer can see: posture, speed, direction, ground contact, camera movement, clothing motion and environmental response; replace the single verb 'running' with speed, effort, posture, surface contact and camera relationship; Kling 3.0 supports up to 15 s with multi-shot. Hailuo's page (creator-style claims): keep one major motion per clip - if the subject moves fast keep the camera static or use a simple slow push-in, because combining a sprint with a dolly zoom or whip pan breaks temporal logic; it also describes ghosting as trailing limbs. Evidence quality. Hailuo labels its 'Velocity-to-Artifact' model as hypothetical and not lab-tested, built from internal pattern recognition. Method (inference). Write each motion as 3-4 visible cues; assign only one dominant motion (subject or camera)...
Structured fields
{
"citations": [
{
"url": "https://kling.ai/blog/kling-ai-motion-prompts-guide",
"note": "intro; Running; 02 One Major Motion Per Clip; 06 Modeling Note; method"
},
{
"url": "https://hailuoai.video/pages/knowledge/fix-motion-ghosting-ai-video",
"note": "intro; Running; 02 One Major Motion Per Clip; 06 Modeling Note; method"
}
]
}Evidence claims
- [sourced_fact] Problem. Text-only motion prompts give vague or ghosted movement. Conditions. I2V/T2V prompts of 4-15 s clips. Vendor statements. Kling's guide: motion prompts work best when they describe what the viewer can see: posture, speed, direction, ground contact, camera movement, clothing motion and environmental response; replace the single verb 'running' with speed, effort, posture, surface contact and camera relationship; Kling 3.0 supports up to 15 s with multi-shot. Hailuo's page (creator-style claims): keep one major motion per clip - if the subject moves fast keep the camera static or use a simple slow push-in, because combining a sprint with a dolly zoom or whip pan breaks temporal logic; it also describes ghosting as trailing limbs. Evidence quality. Hailuo labels its 'Velocity-to-Artifact' model as hypothetical and not lab-tested, built from internal pattern recognition. Method (inference). Write each motion as 3-4 visible cues; assign only one dominant motion (subject or camera) per clip; if motion must combine, split into two clips and cut on action (see C3-B576-13). Failure modes. Ghosting or smeared limbs at high velocity (per Hailuo, unverified). Limitations. No quantitative evidence; pages are vendor guidance. Version/date. Kling blog Jul 3, 2026; Hailuo page July 2026; fetched 2026-10-23. · locator: intro; Running; 02 One Major Motion Per Clip; 06 Modeling Note; method source
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | unknown | permitted | permitted | unknown | unknown | Applies to this original summary only, not to the cited sources. |