{ jsonpromptstudio }

Kuaishou · updated july 2026

Kling 3.0 JSON prompting guide

Durationexpanded limits; exact caps vary by mode
Resolutionmode-dependent
FPSmode-dependent
Audionative audio-visual output
Multi-shotyes

Last verified 2026-07-11. Sources: Kling: VIDEO 3.0 Omni model guide , Kling: VIDEO 3.0 model guide , Kling: text-to-video prompt guide

multi-shot sequenceslip-syncmotion controlelement consistency

Kling 3.0 is strongest when you treat the prompt like a directed scene: subject, movement, scene, camera language and lighting. Its official guides emphasize native audio-visual output, element references and multi-shot storyboarding; exact duration and resolution caps vary by mode, so keep this site conservative where the public docs are not explicit.

How to prompt Kling 3.0 with JSON

Kling prompt guidance is scene-aware: write the action block like a director's shot note rather than a keyword list. For multi-shot work, structure the action as concise shot beats and keep the style block identical across beats.

Where references help

Use element references when the product, outfit, character or scene must stay stable across movement. If a brand object matters, a real reference image is more reliable than text alone.

Where to run it

The official Kling app has the full feature set. Some third-party hosts expose Kling alongside Seedance and Wan, which is useful for cross-model testing, but public specs can vary by host and mode.

Prompting rules for Kling 3.0

Example template, Kling 3.0-shaped

The Kling 3.0 tab shows this site's block order for the model. Browse all 438 templates.

Google · duration 4s, 6s, or 8s (8s required for 1080p, 4K, or reference images) · 720p, 1080p, or 4K · audio native · verified 2026-07-11 - click any value to edit
{
  "scene": "Downtown street at golden hour, soft haze",
  "subject": "Young woman with brown hair and denim jacket",
  "action": "Walks toward camera through light traffic",
  "camera": {
    "lens_mm": 35,
    "movement": "dolly_in",
    "movement_speed": "slow"
  },
  "style": "Cinematic, natural light, gentle contrast",
  "audio": "Soft indie guitar",
  "technical": {
    "aspect_ratio": "16:9",
    "seed": 137421,
    "lock_identity": true,
    "lock_style": true,
    "negative_prompt": "extra people, text overlays, hands",
    "duration_seconds": 8,
    "fps": 24,
    "creativity": 0.4
  }
}
  • Veo 3.1 follows structured prompts unusually well: lock camera, lighting and audio as separate JSON fields.
  • Native audio: describe dialogue, ambient sound and music directly in the audio field.
Kuaishou · duration expanded limits; exact caps vary by mode · mode-dependent · audio native audio-visual output · verified 2026-07-11 - click any value to edit
{
  "subject": "Young woman with brown hair and denim jacket",
  "action": "Walks toward camera through light traffic",
  "scene": "Downtown street at golden hour, soft haze",
  "camera": {
    "lens_mm": 35,
    "movement": "dolly_in",
    "movement_speed": "slow"
  },
  "style": "Cinematic, natural light, gentle contrast",
  "audio": "Soft indie guitar",
  "technical": {
    "aspect_ratio": "16:9",
    "seed": 137421,
    "lock_identity": true,
    "lock_style": true,
    "negative_prompt": "extra people, text overlays, hands",
    "duration_seconds": 8,
    "fps": 24,
    "creativity": 0.4
  }
}
  • Kling prompt guidance emphasizes Subject, Movement, Scene, Camera Language and Lighting.
  • Write the action field as a shot note, not a keyword list.
ByteDance · duration 4-15s · 480p, 720p, 1080p, 4K ratios in Runway API · audio native synchronized audio on supported hosts · verified 2026-07-11 - click any value to edit
{
  "camera": {
    "lens_mm": 35,
    "movement": "dolly_in",
    "movement_speed": "slow"
  },
  "subject": "Young woman with brown hair and denim jacket",
  "action": "Walks toward camera through light traffic",
  "scene": "Downtown street at golden hour, soft haze",
  "style": "Cinematic, natural light, gentle contrast",
  "audio": "Soft indie guitar",
  "technical": {
    "aspect_ratio": "16:9",
    "seed": 137421,
    "lock_identity": true,
    "lock_style": true,
    "negative_prompt": "extra people, text overlays, hands",
    "duration_seconds": 8,
    "fps": 24,
    "creativity": 0.4
  }
}
  • Use a strict block order: CAMERA -> SUBJECT -> ACTION -> ENVIRONMENT -> LIGHTING -> STYLE.
  • Keep the camera block to a shot type plus one movement; stacking moves degrades output.
Alibaba · duration workflow-dependent · 720p open-weights TI2V · audio none in base text/image-to-video pipeline · verified 2026-07-11 - click any value to edit
{
  "subject": "Young woman with brown hair and denim jacket",
  "action": "Walks toward camera through light traffic",
  "scene": "Downtown street at golden hour, soft haze",
  "camera": {
    "lens_mm": 35,
    "movement": "dolly_in",
    "movement_speed": "slow"
  },
  "style": "Cinematic, natural light, gentle contrast",
  "technical": {
    "aspect_ratio": "16:9",
    "seed": 137421,
    "lock_identity": true,
    "lock_style": true,
    "negative_prompt": "extra people, text overlays, hands",
    "duration_seconds": 8,
    "fps": 24,
    "creativity": 0.4
  }
}
  • Wan 2.2 is the latest version with genuinely open, downloadable weights.
  • Open-weights Wan 2.2 has no native audio track in the base text/image-to-video pipeline.
Runway · duration 2-10s · 720p; output dimensions vary by aspect ratio · audio none in video generation · verified 2026-07-11 - click any value to edit
{
  "subject": "Young woman with brown hair and denim jacket",
  "action": "Walks toward camera through light traffic",
  "camera": {
    "lens_mm": 35,
    "movement": "dolly_in",
    "movement_speed": "slow"
  },
  "scene": "Downtown street at golden hour, soft haze",
  "style": "Cinematic, natural light, gentle contrast",
  "technical": {
    "aspect_ratio": "16:9",
    "seed": 137421,
    "lock_identity": true,
    "lock_style": true,
    "negative_prompt": "extra people, text overlays, hands",
    "duration_seconds": 8,
    "fps": 24,
    "creativity": 0.4
  }
}
  • Runway recommends clear, direct language; text-to-video should describe both visual elements and motion.
  • Image-to-video prompts should focus on describing the motion of the scene.

Run Kling 3.0

Other model guides