{ jsonpromptstudio }

Ad & UGC Flagships

Restaurant: Table Pullback

A local restaurant ad that shows plated food, atmosphere and a human handoff.. Best for: Restaurants, cafes, food delivery, hospitality ads.

restaurantfoodlocal businesshospitalitytabletop

  1. Pick your model's tab — the JSON re-shapes itself to that model's block order and limits.
  2. Click any green value to edit it in place — swap the subject, setting, or style for your own.
  3. Copy and paste the JSON as your prompt in the tool — links below.
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": "Hero dish or plated meal reference image.",
    "style_frame": "Warm restaurant tabletop with shallow depth of field and visible ambience.",
    "model_handling": "Supports image inputs and reference-driven workflows; use product or style frames when exact object appearance matters."
  },
  "brand": {
    "hex_colors": "#7C2D12, #FACC15, #FFF7ED",
    "logo_handling": "Do not create menu text; use real menu/logo overlays in post.",
    "tone": "warm, craveable, local"
  },
  "scene": "Cozy restaurant table at dinner service with candlelight and warm background blur",
  "subject": "Server places a signature dish onto a table where two guests are reaching for drinks",
  "action": "Camera starts tight on steam rising from the dish, then pulls back as the server sets it down and guests react",
  "camera": {
    "movement": "slow pullback from macro food detail to table scene",
    "lens_mm": 50,
    "distance": "macro to medium table shot"
  },
  "lighting": {
    "type": "warm practical restaurant light",
    "quality": "soft candle glow, appetizing highlights on food"
  },
  "style": "local restaurant commercial, sensory food detail, human warmth",
  "audio": "plate set-down, quiet dining room ambience, subtle warm music",
  "technical": {
    "aspect_ratio": "9:16",
    "duration_seconds": 8,
    "fps": 24,
    "negative_prompt": "unappetizing food texture, fake menu text, distorted hands, spills, overdone steam"
  }
}
  • 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": "Hero dish or plated meal reference image.",
    "style_frame": "Warm restaurant tabletop with shallow depth of field and visible ambience.",
    "model_handling": "Use element references for products, outfits, characters or scenes when consistency matters."
  },
  "brand": {
    "hex_colors": "#7C2D12, #FACC15, #FFF7ED",
    "logo_handling": "Do not create menu text; use real menu/logo overlays in post.",
    "tone": "warm, craveable, local"
  },
  "subject": "Server places a signature dish onto a table where two guests are reaching for drinks",
  "action": "Camera starts tight on steam rising from the dish, then pulls back as the server sets it down and guests react",
  "scene": "Cozy restaurant table at dinner service with candlelight and warm background blur",
  "camera": {
    "movement": "slow pullback from macro food detail to table scene",
    "lens_mm": 50,
    "distance": "macro to medium table shot"
  },
  "lighting": {
    "type": "warm practical restaurant light",
    "quality": "soft candle glow, appetizing highlights on food"
  },
  "style": "local restaurant commercial, sensory food detail, human warmth",
  "audio": "plate set-down, quiet dining room ambience, subtle warm music",
  "technical": {
    "aspect_ratio": "9:16",
    "duration_seconds": 8,
    "fps": 24,
    "negative_prompt": "unappetizing food texture, fake menu text, distorted hands, spills, overdone steam"
  }
}
  • 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": "Hero dish or plated meal reference image.",
    "style_frame": "Warm restaurant tabletop with shallow depth of field and visible ambience.",
    "model_handling": "Hosted Seedance 2 workflows support reference image, video and audio inputs; keep reference intent explicit."
  },
  "brand": {
    "hex_colors": "#7C2D12, #FACC15, #FFF7ED",
    "logo_handling": "Do not create menu text; use real menu/logo overlays in post.",
    "tone": "warm, craveable, local"
  },
  "camera": {
    "movement": "slow pullback from macro food detail to table scene",
    "lens_mm": 50,
    "distance": "macro to medium table shot"
  },
  "subject": "Server places a signature dish onto a table where two guests are reaching for drinks",
  "action": "Camera starts tight on steam rising from the dish, then pulls back as the server sets it down and guests react",
  "scene": "Cozy restaurant table at dinner service with candlelight and warm background blur",
  "lighting": {
    "type": "warm practical restaurant light",
    "quality": "soft candle glow, appetizing highlights on food"
  },
  "style": "local restaurant commercial, sensory food detail, human warmth",
  "audio": "plate set-down, quiet dining room ambience, subtle warm music",
  "technical": {
    "aspect_ratio": "9:16",
    "duration_seconds": 8,
    "fps": 24,
    "negative_prompt": "unappetizing food texture, fake menu text, distorted hands, spills, overdone steam"
  }
}
  • 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": "Hero dish or plated meal reference image.",
    "style_frame": "Warm restaurant tabletop with shallow depth of field and visible ambience.",
    "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": "#7C2D12, #FACC15, #FFF7ED",
    "logo_handling": "Do not create menu text; use real menu/logo overlays in post.",
    "tone": "warm, craveable, local"
  },
  "subject": "Server places a signature dish onto a table where two guests are reaching for drinks",
  "action": "Camera starts tight on steam rising from the dish, then pulls back as the server sets it down and guests react",
  "scene": "Cozy restaurant table at dinner service with candlelight and warm background blur",
  "camera": {
    "movement": "slow pullback from macro food detail to table scene",
    "lens_mm": 50,
    "distance": "macro to medium table shot"
  },
  "lighting": {
    "type": "warm practical restaurant light",
    "quality": "soft candle glow, appetizing highlights on food"
  },
  "style": "local restaurant commercial, sensory food detail, human warmth",
  "technical": {
    "aspect_ratio": "9:16",
    "duration_seconds": 8,
    "fps": 24,
    "negative_prompt": "unappetizing food texture, fake menu text, distorted hands, spills, overdone steam"
  }
}
  • 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": "Hero dish or plated meal reference image.",
    "style_frame": "Warm restaurant tabletop with shallow depth of field and visible ambience.",
    "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": "#7C2D12, #FACC15, #FFF7ED",
    "logo_handling": "Do not create menu text; use real menu/logo overlays in post.",
    "tone": "warm, craveable, local"
  },
  "subject": "Server places a signature dish onto a table where two guests are reaching for drinks",
  "action": "Camera starts tight on steam rising from the dish, then pulls back as the server sets it down and guests react",
  "camera": {
    "movement": "slow pullback from macro food detail to table scene",
    "lens_mm": 50,
    "distance": "macro to medium table shot"
  },
  "scene": "Cozy restaurant table at dinner service with candlelight and warm background blur",
  "lighting": {
    "type": "warm practical restaurant light",
    "quality": "soft candle glow, appetizing highlights on food"
  },
  "style": "local restaurant commercial, sensory food detail, human warmth",
  "technical": {
    "aspect_ratio": "9:16",
    "duration_seconds": 8,
    "fps": 24,
    "negative_prompt": "unappetizing food texture, fake menu text, distorted hands, spills, overdone steam"
  }
}
  • 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 this prompt

Copy the JSON above, then paste it as your prompt in any of these tools. Veo 3.1 is free to try inside Gemini (daily limit applies).

Veo 3.1 — free in Gemini ↗Veo 3.1 — Google Flow ↗Kling 3.0 — official app ↗Higgsfield — Kling, Seedance & Wan ↗fal.ai — API playground ↗Seedance 2.0 — Dreamina ↗Runway Gen-4.5 ↗

What each block does

BlockPurpose
referencesOptional image inputs: product, character face, or style frame. Use these where the model supports references; otherwise treat them as setup notes.
brandBrand constraints: colors, logo handling and voice. Models approximate hex colors and cannot render exact logos reliably; use a reference image or add exact logos in post.
sceneWhere it happens: location, time of day, weather, mood of the space.
subjectWho or what the shot is about. Keep it to one clear subject — models blur focus when given several.
actionWhat visibly happens during the clip. Describe motion the camera can see, not internal states.
cameraShot framing and movement. One movement per clip reads best on every current model.
lightingLight source, quality and shadow behavior. The single highest-leverage block for realism.
styleAesthetic direction: film stock, color palette, references, tone.
audioDialogue, ambient sound and music. Only Veo 3.1, Kling 3.0 and Seedance 2.0 render audio natively.
technicalRender settings: aspect ratio, duration, fps, seed for reproducibility, negative prompt.

More ad & ugc flagships prompts

all →

Premium Product Hero: Rain Reflection

A high-polish product reveal built for beauty, fragrance, tech accessories or packaged goods.

UGC Testimonial: Bathroom Mirror Proof

A creator-style testimonial that feels native to TikTok while still giving the model clear shot control.

Unboxing Hook: First Three Seconds

A tactile unboxing sequence that prioritizes the opening hook and product reveal.

Before/After: Cleaning Transformation

A conversion-friendly transformation shot with a clear visual payoff.