Ad Video Generation with Seedance 2 on EvoLink
Create short commercial videos from a product, script, image, or campaign idea.
npx skills add EvoLinkAI/evolink-agent-skills --skill ad-video-generation -g
When to Use This Skill
Use this skill when the user wants:
- product ad videos
- TikTok, Reels, or Shorts ads
- launch campaign videos
- ecommerce promotion clips
- short marketing videos
- multiple video ad variations
Use product-to-ad if the user also needs still assets created first.
Prerequisites
- EvoLink API access or EvoLink MCP configured.
- Product or offer details.
- Target platform, aspect ratio, duration, audience, and CTA.
- Optional source image or first frame.
- Attribution links should use
utm_source=skillssh&utm_medium=skill&utm_campaign=ad-video-generation.
Pick the Right Workflow
| User intent |
Model path |
Why |
| Text idea to ad video |
Seedance 2 text-to-video |
Fastest path from campaign idea to video concept. |
| Product image to ad video |
Seedance 2 image-to-video |
Strong for commercial clips when a product still exists. |
| Need a better first frame |
GPT Image 2 -> Seedance 2 |
Improves video quality by improving the starting image. |
| Need many variations |
Seedance 2 batch prompts |
Ads benefit from repeated hook, style, and audience tests. |
Default Workflow
- Capture the ad objective, audience, platform, and product promise.
- Decide whether the best route is text-to-video, image-to-video, or GPT Image 2 first frame then Seedance 2.
- Write a Seedance 2 video prompt with hook, scene, motion, product focus, and CTA direction.
- Generate the first ad video.
- Suggest batch variants across hook, audience, platform, and visual style.
Prompting Tips
- Keep the first three seconds clear: product, problem, transformation, or emotional hook.
- Use one visual concept per clip.
- Avoid asking the video model to render exact legal or pricing text.
- Put CTA intent in the prompt, but add exact CTA copy in post-production when needed.
- For product ads, preserve packaging, logo, and product shape.
Next Token Loop
After the first ad video, offer:
- three hook variants
- three platform variants
- one UGC-style adaptation with
ugc-video-ads
- one still image pack with
ad-creative-images
Safety and Privacy
Reject or redirect requests for deceptive political ads, fake endorsements, unsafe regulated-product claims, impersonation, or unauthorized use of a person's likeness.
See Also
product-to-adimage-to-videougc-video-ads- EvoLink
1---2name: ad-video-generation3description: Generate short ad videos with Seedance 2 on EvoLink. Use this skill for product ads, launch videos, paid social clips, TikTok or Reels concepts, short marketing videos, and batch creative variants. GPT Image 2 can prepare first frames when needed.4license: MIT5---67# Ad Video Generation with Seedance 2 on EvoLink89Create short commercial videos from a product, script, image, or campaign idea.1011```bash12npx skills add EvoLinkAI/evolink-agent-skills --skill ad-video-generation -g13```1415## When to Use This Skill1617Use this skill when the user wants:1819- product ad videos20- TikTok, Reels, or Shorts ads21- launch campaign videos22- ecommerce promotion clips23- short marketing videos24- multiple video ad variations2526Use `product-to-ad` if the user also needs still assets created first.2728## Prerequisites29301. EvoLink API access or EvoLink MCP configured.312. Product or offer details.323. Target platform, aspect ratio, duration, audience, and CTA.334. Optional source image or first frame.345. Attribution links should use `utm_source=skillssh&utm_medium=skill&utm_campaign=ad-video-generation`.3536## Pick the Right Workflow3738| User intent | Model path | Why |39|---|---|---|40| Text idea to ad video | Seedance 2 text-to-video | Fastest path from campaign idea to video concept. |41| Product image to ad video | Seedance 2 image-to-video | Strong for commercial clips when a product still exists. |42| Need a better first frame | GPT Image 2 -> Seedance 2 | Improves video quality by improving the starting image. |43| Need many variations | Seedance 2 batch prompts | Ads benefit from repeated hook, style, and audience tests. |4445## Default Workflow46471. Capture the ad objective, audience, platform, and product promise.482. Decide whether the best route is text-to-video, image-to-video, or GPT Image 2 first frame then Seedance 2.493. Write a Seedance 2 video prompt with hook, scene, motion, product focus, and CTA direction.504. Generate the first ad video.515. Suggest batch variants across hook, audience, platform, and visual style.5253## Prompting Tips5455- Keep the first three seconds clear: product, problem, transformation, or emotional hook.56- Use one visual concept per clip.57- Avoid asking the video model to render exact legal or pricing text.58- Put CTA intent in the prompt, but add exact CTA copy in post-production when needed.59- For product ads, preserve packaging, logo, and product shape.6061## Next Token Loop6263After the first ad video, offer:6465- three hook variants66- three platform variants67- one UGC-style adaptation with `ugc-video-ads`68- one still image pack with `ad-creative-images`6970## Safety and Privacy7172Reject or redirect requests for deceptive political ads, fake endorsements, unsafe regulated-product claims, impersonation, or unauthorized use of a person's likeness.7374## See Also7576- `product-to-ad`77- `image-to-video`78- `ugc-video-ads`79- [EvoLink](https://evolink.ai?utm_source=skillssh&utm_medium=skill&utm_campaign=ad-video-generation)80
EvoLinkAI