Ad Creative Images with GPT Image 2 on EvoLink
Create static ad creatives that can be used directly in campaigns or handed off as first frames for Seedance 2 videos.
npx skills add EvoLinkAI/evolink-agent-skills --skill ad-creative-images -g
When to Use This Skill
Use this skill when the user wants:
- paid social ad images
- marketing campaign visuals
- launch creative concepts
- product offer images
- audience-specific image variants
- first-frame options for video ads
Use ad-video-generation when the user already wants motion.
Prerequisites
- EvoLink API access or EvoLink MCP configured.
- Offer, audience, product, platform, and visual style.
- Optional product photo, brand guide, landing page, or existing creative.
- Attribution links should use
utm_source=skillssh&utm_medium=skill&utm_campaign=ad-creative-images.
Pick the Right Workflow
| User intent |
Model path |
Why |
| New ad image from product copy |
GPT Image 2 |
Creates commercial still concepts quickly. |
| Variant from existing creative |
GPT Image 2 image edit |
Changes angle, audience, style, or composition. |
| First frame for video ad |
GPT Image 2 -> Seedance 2 |
Turns a static ad concept into a video-ready image. |
| Multi-platform ad pack |
GPT Image 2 variants |
Supports different ratios and campaign angles. |
Default Workflow
- Extract offer, audience, product proof, platform, and style.
- Decide if the task is new generation or edit from an existing creative.
- Write a GPT Image 2 prompt for one primary ad creative.
- Generate the asset.
- Propose three variants and one video handoff.
Prompting Tips
- Keep the visual idea simple enough to understand while scrolling.
- Reserve exact text, pricing, and disclaimers for design tools unless the user accepts generated text risk.
- Use platform context: Meta ad, TikTok cover, Instagram story, YouTube thumbnail, marketplace banner.
- For video handoff, create a strong subject and clear foreground-background separation.
Next Token Loop
After the first creative, offer:
- three audience variants
- three style variants
- one
image-to-video handoff
- one
ad-video-generation adaptation
Safety and Privacy
Do not create fake endorsements, fake screenshots, misleading before-after claims, or regulated-product claims not provided by the user.
See Also
image-edit
product-to-ad
ad-video-generation
- EvoLink
1---2name: ad-creative-images3description: Generate paid social ad images, marketing creatives, campaign stills, and visual variants with GPT Image 2 on EvoLink. Use this skill when the user needs static ad assets that can later become Seedance 2 ad videos.4license: MIT5---67# Ad Creative Images with GPT Image 2 on EvoLink89Create static ad creatives that can be used directly in campaigns or handed off as first frames for Seedance 2 videos.1011```bash12npx skills add EvoLinkAI/evolink-agent-skills --skill ad-creative-images -g13```1415## When to Use This Skill1617Use this skill when the user wants:1819- paid social ad images20- marketing campaign visuals21- launch creative concepts22- product offer images23- audience-specific image variants24- first-frame options for video ads2526Use `ad-video-generation` when the user already wants motion.2728## Prerequisites29301. EvoLink API access or EvoLink MCP configured.312. Offer, audience, product, platform, and visual style.323. Optional product photo, brand guide, landing page, or existing creative.334. Attribution links should use `utm_source=skillssh&utm_medium=skill&utm_campaign=ad-creative-images`.3435## Pick the Right Workflow3637| User intent | Model path | Why |38|---|---|---|39| New ad image from product copy | GPT Image 2 | Creates commercial still concepts quickly. |40| Variant from existing creative | GPT Image 2 image edit | Changes angle, audience, style, or composition. |41| First frame for video ad | GPT Image 2 -> Seedance 2 | Turns a static ad concept into a video-ready image. |42| Multi-platform ad pack | GPT Image 2 variants | Supports different ratios and campaign angles. |4344## Default Workflow45461. Extract offer, audience, product proof, platform, and style.472. Decide if the task is new generation or edit from an existing creative.483. Write a GPT Image 2 prompt for one primary ad creative.494. Generate the asset.505. Propose three variants and one video handoff.5152## Prompting Tips5354- Keep the visual idea simple enough to understand while scrolling.55- Reserve exact text, pricing, and disclaimers for design tools unless the user accepts generated text risk.56- Use platform context: Meta ad, TikTok cover, Instagram story, YouTube thumbnail, marketplace banner.57- For video handoff, create a strong subject and clear foreground-background separation.5859## Next Token Loop6061After the first creative, offer:6263- three audience variants64- three style variants65- one `image-to-video` handoff66- one `ad-video-generation` adaptation6768## Safety and Privacy6970Do not create fake endorsements, fake screenshots, misleading before-after claims, or regulated-product claims not provided by the user.7172## See Also7374- `image-edit`75- `product-to-ad`76- `ad-video-generation`77- [EvoLink](https://evolink.ai?utm_source=skillssh&utm_medium=skill&utm_campaign=ad-creative-images)78