Communitygithub.com

awesome-genmedia/skills

Create product showcase video ads using each::sense AI. Generate cinematic product reveal videos, unboxing sequences, feature highlight clips, and social media video ads for e-commerce marketing. Supports various formats for Instagram, TikTok, YouTube, and website hero videos. Use for: product launch videos, social media ads, DTC brand videos, Shopify hero videos, promotional clips, product demos. Triggers: product video, product ad video, video ad, product commercial, product showcase video, product promo, social media video ad, product reveal, unboxing video, commercial video

Was ist skills?

skills is a Claude Code agent skill that create product showcase video ads using each::sense AI. Generate cinematic product reveal videos, unboxing sequences, feature highlight clips, and social media video ads for e-commerce marketing. Supports various formats for Instagram, TikTok, YouTube, and website hero videos. Use for: product launch videos, social media ads, DTC brand videos, Shopify hero videos, promotional clips, product demos. Triggers: product video, product ad video, video ad, product commercial, product showcase video, product promo, social media video ad, product reveal, unboxing video, commercial video.

Funktioniert mit✓Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/awesome-genmedia/skills/tree/HEAD/categories/ecommerce/ai-product-video-ad

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

Dokumentation

AI Product Video Ad

Create product showcase video ads and promotional clips using each::sense — the intelligent AI agent that automatically selects the best model for your request.

Quick Start

Requires an each::labs API key. Get one at eachlabs.ai.

Using curl

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": "Generate a product video ad: a sleek matte black wireless speaker slowly rotates on a reflective dark surface, studio lighting creating clean highlights on the curved edges. Camera slowly orbits around the product. Minimal, premium aesthetic, dark background with subtle blue accent light, 4K commercial quality"
      }
    ],
    "stream": false
  }'

Using Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_EACHLABS_API_KEY",
    base_url="https://eachsense-agent.core.eachlabs.run/v1"
)

response = client.chat.completions.create(
    model="eachsense/beta",
    messages=[{
        "role": "user",
        "content": "Generate a product video ad: a sleek matte black wireless speaker slowly rotates on a reflective dark surface, studio lighting creating clean highlights on the curved edges. Camera slowly orbits around the product. Minimal, premium aesthetic, dark background with subtle blue accent light, 4K commercial quality"
    }]
)

print(response.choices[0].message.content)

With Reference Image

Provide your product photo to animate it:

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": [
              {"type": "text", "text": "Create a product video ad from this product image. The product smoothly descends into frame from above and lands softly on a marble surface. Camera pushes in slowly for a close-up. Dramatic studio lighting, premium feel, commercial video quality."},
              {"type": "image_url", "image_url": {"url": "https://example.com/my-product.jpg"}}
            ]
          }
    ],
    "stream": false
  }'

Images are sent inside messages using the OpenAI multimodal content format. Maximum 4 images per request.

Streaming

Set "stream": true for real-time SSE responses, or "stream": false for complete result in a single response. Streaming is useful for showing progress in UIs; non-streaming is simpler for scripts and automation.

Video Ad Formats

FormatAspect RatioDurationPlatform
Instagram Reel9:16 vertical15-30sInstagram, TikTok
YouTube Pre-Roll16:9 horizontal6-15sYouTube
Website Hero16:9 horizontal5-15s (loop)Shopify, brand sites
Story Ad9:16 vertical5-15sInstagram, Snapchat
Square Social1:1 square15-30sFacebook, Instagram feed

Shot Types for Product Videos

ShotMotionEffect
Product Orbitcamera circles the static productshows all angles, premium feel
Drop Revealproduct falls/descends into framedramatic entrance
Push-Incamera moves toward productdraws attention to detail
Turntableproduct rotates on a platform360-degree view
Lifestyle Cutproduct in use by a personcontext and aspiration
Macro Detailextreme close-up gliding over surfacetexture and craft
Exploded Viewcomponents separate and reassembleengineering / feature callout

Prompt Engineering Tips

Prompt Structure

"Generate a product video ad:" + [product description] + [motion/animation] + [camera movement] + [setting and lighting] + [mood and quality]

Motion Keywords

slowly rotates, gently descends, smoothly slides into frame,
orbiting camera, push-in close-up, tracking alongside,
parallax movement, subtle floating hover, product assembling

Lighting for Video

studio three-point lighting, dramatic rim light,
soft diffused top light, colored accent backlight,
natural golden hour, high-key bright and clean,
low-key dark and moody, volumetric light beams

Examples

Skincare Product Reveal

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": "Generate a product video ad for a luxury skincare serum: a frosted glass bottle with a gold dropper cap descends slowly through soft mist onto a white marble surface. A single water droplet falls onto the marble and ripples outward. Camera pushes in to a close-up of the dropper releasing a golden serum drop. Soft diffused lighting, clean white and gold palette, luxurious spa aesthetic, 9:16 vertical format for Instagram."
      }
    ],
    "stream": false
  }'

Tech Product Launch

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": "Generate a product video ad for a smartwatch: starts with a dark screen, a beam of light sweeps across revealing the watch face glowing on a dark surface. Camera orbits around the watch showing the slim profile and metal band. The screen lights up showing a fitness dashboard. Sleek modern tech aesthetic, dark background with blue accent lighting, cinematic lens flare, Apple-style product commercial, 16:9 landscape."
      }
    ],
    "stream": false
  }'

Food Product Social Ad

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": "Generate a product video ad for artisanal chocolate bars: a hand slowly unwraps gold foil to reveal a dark chocolate bar, then breaks it in half with a satisfying snap. Close-up of the cross-section showing rich texture. Melted chocolate drizzles in the background. Warm moody lighting, dark wood surface, premium food photography video style, slow motion detail, 1:1 square format."
      }
    ],
    "stream": false
  }'

Sneaker Drop Announcement

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": "Generate a product video ad for a sneaker release: a pair of white and neon green sneakers drops from above and lands on a concrete surface with a puff of powder. Camera orbits around the shoes at ground level, showing the sole tread and knit upper texture. Urban graffiti wall in the blurred background. Streetwear aesthetic, bass-heavy energy feel, dynamic camera, 9:16 vertical for TikTok."
      }
    ],
    "stream": false
  }'

Multi-Scene Ad Workflow

PRODUCT="a premium leather wallet in cognac brown"
STYLE="warm studio lighting, dark background, luxury commercial quality"

SCENES=(
  "Scene 1 — Reveal: the wallet slowly slides into frame on a dark leather surface, camera positioned low, dramatic side lighting"
  "Scene 2 — Detail: extreme close-up tracking along the wallet edge showing hand-stitched seams and grain texture"
  "Scene 3 — Feature: the wallet opens to reveal card slots, a person's hand slides a card in and out smoothly"
  "Scene 4 — Lifestyle: a well-dressed man at a restaurant table casually places the wallet beside a glass of whiskey, shallow depth of field"
  "Scene 5 — End card: the wallet centered on a dark surface, camera slowly pulling back, space for text overlay"
)

for SCENE in "${SCENES[@]}"; do
  curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "X-API-Key: $EACHLABS_API_KEY" \
    -d "{
      \"messages\": [{\"role\": \"user\", \"content\": \"Generate a product video ad clip: $PRODUCT. $SCENE. $STYLE\"}],
      \"stream\": false
    }"
  echo "=== SCENE ==="
done

Post-Production Assembly

AI generates individual clips. To create a complete ad:

  1. Generate 3-6 scene clips covering reveal, detail, lifestyle, and end card
  2. Sequence in a video editor — add transitions, adjust timing
  3. Add text overlays — product name, features, price, CTA (AI text is unreliable)
  4. Layer music and sound — choose tracks matching the brand mood
  5. Export for platform — correct aspect ratio and duration per platform

Common Pitfalls

  • Text and logos will not render correctly in video. Add all text in post-production.
  • Too much motion in one clip — keep each clip focused on one movement or action.
  • Product inconsistency — describe the product identically across all scenes for visual coherence.
  • Missing end card space — always generate a final shot with clean negative space for text overlays.
  • Audio is not generated — plan for music and sound design separately.

Related Skills

Related Models

Documentation

Verwandte Skills