{ jsonpromptstudio }

structured prompts for AI video ads

Turn one idea into model-ready ad prompts.

Convert ad, product and UGC ideas into JSON shaped for Veo 3.1, Kling 3.0, Seedance 2.0, Wan and Runway. Start from proven structures with brand, references, audio, negatives and model-specific limits built in.

455 templates
16 ad flagships
5 models supported
$0 no signup, no paywall

start here

What are you making?

Ad & UGC flagships

what are you making? ->

try one

One structure, every model

The same ad structure is automatically re-ordered and adjusted for each model: Seedance wants camera first, Veo carries audio, Wan and Runway drop it.

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
{
  "references": {
    "product_image": "Upload one clean product packshot or hero product image as the main product reference.",
    "style_frame": "Moody premium ad frame: wet pavement, controlled reflections, dark background, precise highlight lines.",
    "notes": "Keep product geometry, label placement and silhouette consistent with the product reference.",
    "model_handling": "Supports image inputs and reference-driven workflows; use product or style frames when exact object appearance matters."
  },
  "brand": {
    "hex_colors": "#0B0E12, #FFB454, #E8E4D9",
    "logo_handling": "Do not invent logo details; preserve from product reference or leave room for logo overlay in post.",
    "tone": "premium, sensory, restrained, confident"
  },
  "scene": "Night studio set dressed like a rainy Tokyo street corner, dark negative space behind the product",
  "subject": "Hero product centered on a glossy rain-soaked surface with tiny water beads on the packaging",
  "action": "A slow highlight sweep reveals the product shape while neon reflections ripple subtly across the surface",
  "camera": {
    "movement": "slow dolly in",
    "lens_mm": 70,
    "distance": "tight product close-up"
  },
  "lighting": {
    "type": "controlled studio key light",
    "direction": "side-lit with narrow rim highlights",
    "quality": "glossy, high-contrast, precise reflections"
  },
  "style": {
    "aesthetic": "luxury commercial, tactile macro detail, cinematic product photography",
    "color_palette": "black, amber, soft ivory, small neon accents"
  },
  "audio": "soft rain bed, subtle low-frequency swell, delicate glass-like shimmer on reveal",
  "technical": {
    "aspect_ratio": "9:16",
    "duration_seconds": 8,
    "fps": 24,
    "negative_prompt": "warped label, extra logos, unreadable text, melted packaging, floating product, hands",
    "lock_style": true
  }
}
  • 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
{
  "references": {
    "product_image": "Upload one clean product packshot or hero product image as the main product reference.",
    "style_frame": "Moody premium ad frame: wet pavement, controlled reflections, dark background, precise highlight lines.",
    "notes": "Keep product geometry, label placement and silhouette consistent with the product reference.",
    "model_handling": "Use element references for products, outfits, characters or scenes when consistency matters."
  },
  "brand": {
    "hex_colors": "#0B0E12, #FFB454, #E8E4D9",
    "logo_handling": "Do not invent logo details; preserve from product reference or leave room for logo overlay in post.",
    "tone": "premium, sensory, restrained, confident"
  },
  "subject": "Hero product centered on a glossy rain-soaked surface with tiny water beads on the packaging",
  "action": "A slow highlight sweep reveals the product shape while neon reflections ripple subtly across the surface",
  "scene": "Night studio set dressed like a rainy Tokyo street corner, dark negative space behind the product",
  "camera": {
    "movement": "slow dolly in",
    "lens_mm": 70,
    "distance": "tight product close-up"
  },
  "lighting": {
    "type": "controlled studio key light",
    "direction": "side-lit with narrow rim highlights",
    "quality": "glossy, high-contrast, precise reflections"
  },
  "style": {
    "aesthetic": "luxury commercial, tactile macro detail, cinematic product photography",
    "color_palette": "black, amber, soft ivory, small neon accents"
  },
  "audio": "soft rain bed, subtle low-frequency swell, delicate glass-like shimmer on reveal",
  "technical": {
    "aspect_ratio": "9:16",
    "duration_seconds": 8,
    "fps": 24,
    "negative_prompt": "warped label, extra logos, unreadable text, melted packaging, floating product, hands",
    "lock_style": true
  }
}
  • 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
{
  "references": {
    "product_image": "Upload one clean product packshot or hero product image as the main product reference.",
    "style_frame": "Moody premium ad frame: wet pavement, controlled reflections, dark background, precise highlight lines.",
    "notes": "Keep product geometry, label placement and silhouette consistent with the product reference.",
    "model_handling": "Hosted Seedance 2 workflows support reference image, video and audio inputs; keep reference intent explicit."
  },
  "brand": {
    "hex_colors": "#0B0E12, #FFB454, #E8E4D9",
    "logo_handling": "Do not invent logo details; preserve from product reference or leave room for logo overlay in post.",
    "tone": "premium, sensory, restrained, confident"
  },
  "camera": {
    "movement": "slow dolly in",
    "lens_mm": 70,
    "distance": "tight product close-up"
  },
  "subject": "Hero product centered on a glossy rain-soaked surface with tiny water beads on the packaging",
  "action": "A slow highlight sweep reveals the product shape while neon reflections ripple subtly across the surface",
  "scene": "Night studio set dressed like a rainy Tokyo street corner, dark negative space behind the product",
  "lighting": {
    "type": "controlled studio key light",
    "direction": "side-lit with narrow rim highlights",
    "quality": "glossy, high-contrast, precise reflections"
  },
  "style": {
    "aesthetic": "luxury commercial, tactile macro detail, cinematic product photography",
    "color_palette": "black, amber, soft ivory, small neon accents"
  },
  "audio": "soft rain bed, subtle low-frequency swell, delicate glass-like shimmer on reveal",
  "technical": {
    "aspect_ratio": "9:16",
    "duration_seconds": 8,
    "fps": 24,
    "negative_prompt": "warped label, extra logos, unreadable text, melted packaging, floating product, hands",
    "lock_style": true
  }
}
  • 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
{
  "references": {
    "product_image": "Upload one clean product packshot or hero product image as the main product reference.",
    "style_frame": "Moody premium ad frame: wet pavement, controlled reflections, dark background, precise highlight lines.",
    "notes": "Keep product geometry, label placement and silhouette consistent with the product reference.",
    "model_handling": "Open-weights Wan 2.2 supports text-to-video and image-to-video; treat product/style references as image-to-video setup notes."
  },
  "brand": {
    "hex_colors": "#0B0E12, #FFB454, #E8E4D9",
    "logo_handling": "Do not invent logo details; preserve from product reference or leave room for logo overlay in post.",
    "tone": "premium, sensory, restrained, confident"
  },
  "subject": "Hero product centered on a glossy rain-soaked surface with tiny water beads on the packaging",
  "action": "A slow highlight sweep reveals the product shape while neon reflections ripple subtly across the surface",
  "scene": "Night studio set dressed like a rainy Tokyo street corner, dark negative space behind the product",
  "camera": {
    "movement": "slow dolly in",
    "lens_mm": 70,
    "distance": "tight product close-up"
  },
  "lighting": {
    "type": "controlled studio key light",
    "direction": "side-lit with narrow rim highlights",
    "quality": "glossy, high-contrast, precise reflections"
  },
  "style": {
    "aesthetic": "luxury commercial, tactile macro detail, cinematic product photography",
    "color_palette": "black, amber, soft ivory, small neon accents"
  },
  "technical": {
    "aspect_ratio": "9:16",
    "duration_seconds": 8,
    "fps": 24,
    "negative_prompt": "warped label, extra logos, unreadable text, melted packaging, floating product, hands",
    "lock_style": true
  }
}
  • 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
{
  "references": {
    "product_image": "Upload one clean product packshot or hero product image as the main product reference.",
    "style_frame": "Moody premium ad frame: wet pavement, controlled reflections, dark background, precise highlight lines.",
    "notes": "Keep product geometry, label placement and silhouette consistent with the product reference.",
    "model_handling": "Gen-4.5 supports text-to-video and image-to-video; reference images are often more important than long prompt text for consistency."
  },
  "brand": {
    "hex_colors": "#0B0E12, #FFB454, #E8E4D9",
    "logo_handling": "Do not invent logo details; preserve from product reference or leave room for logo overlay in post.",
    "tone": "premium, sensory, restrained, confident"
  },
  "subject": "Hero product centered on a glossy rain-soaked surface with tiny water beads on the packaging",
  "action": "A slow highlight sweep reveals the product shape while neon reflections ripple subtly across the surface",
  "camera": {
    "movement": "slow dolly in",
    "lens_mm": 70,
    "distance": "tight product close-up"
  },
  "scene": "Night studio set dressed like a rainy Tokyo street corner, dark negative space behind the product",
  "lighting": {
    "type": "controlled studio key light",
    "direction": "side-lit with narrow rim highlights",
    "quality": "glossy, high-contrast, precise reflections"
  },
  "style": {
    "aesthetic": "luxury commercial, tactile macro detail, cinematic product photography",
    "color_palette": "black, amber, soft ivory, small neon accents"
  },
  "technical": {
    "aspect_ratio": "9:16",
    "duration_seconds": 8,
    "fps": 24,
    "negative_prompt": "warped label, extra logos, unreadable text, melted packaging, floating product, hands",
    "lock_style": true
  }
}
  • 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.

Template library

all 87 categories ->

Viral video formats

all formats ->

Model guides

all guides ->