FreeVideo
App window with zoom
- 365365 downloads
- 125125 likes
- 188188 saves
Works with
+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
Generate AI images with Gemini and GPT Image v1.0.0
Use this resource to generate images for a website, poster or social media with AI
New
- 533 downloads
- 164 likes
- 250 saves
- OpenAI / Google Gemini key required
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install ai-image-api-generatorWith no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent picks the right model: Gemini for scenes, GPT Image 2 for readable text and batches of variants, GPT Image 1.5 for transparent backgrounds. It builds the prompt with a 5-part framework, calls the API, saves the images and can check or edit them over several turns. You get hero banners, icons, posters and product shots ready to use.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Works in
- Install guides
- Generates with
- GPT Image 2
- Uses
- OpenAI / Google Gemini
- Python 3
- Pillow library (optional, for WebP conversion)
- Licence
- MIT
Similar resources
View all- Free
FreeVideo
One big number
- 463463 downloads
- 223223 likes
- 100100 saves
Works with+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
PROVideo
PalateKit Motion, the library
- 338338 downloads
- 198198 likes
- 249249 saves
Works with+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
PROVideo
Three bars head to head
- 348348 downloads
- 133133 likes
- 182182 saves
Works with+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
PROVideo
Before / after slider
- 322322 downloads
- 248248 likes
- 238238 saves
Works with+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
PROVideo
Three-card carousel
- 418418 downloads
- 157157 likes
- 101101 saves
Works with+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
PROVideo
Chat exchange
- 564564 downloads
- 127127 likes
- 161161 saves
Works with+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
PROVideo
Checklist ticking off
- 442442 downloads
- 233233 likes
- 160160 saves
Works with+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- SKILL.md: model selection table, prompt framework, Python API call examples, multi-turn editing
- references/prompting-guide.md: photo parameters (lighting, focal length, aperture) and style presets
- A table of image formats by use (banner, OG, story, avatar)
Good fit for
- Creating visuals for a showcase site, a shop or a launch
- Producing a poster or a share image with readable text
- Exploring ten variants of one concept before choosing
Not for
- Working without an API key or an account with an image provider
- Creating vector logos or editable illustrations
- Using an agent other than Claude Code
Tags
- ai images
- gemini
- gpt image
- prompting
- hero banner
About
You say
"Generate a 16:9 hero banner for my massage studio website, warm light, no text."
Skill published by jezweb under the MIT license.
Show moreShow less
Prerequisites
- You bring
- A Google Gemini or OpenAI API key and A description of the visual you want and its use
- Dependencies
- Python 3 and Pillow library (optional, for WebP conversion)
- External costs
- Calls billed by Google or OpenAI depending on model and quality Billed by the provider, on your account.
How to use it
- Set GEMINI_API_KEY or OPENAI_API_KEY in your environment
- Describe the visual and where it will be used; the agent picks the model and format
- Compare the images, then ask for edits while stating what to keep
Content preview
Files
- LICENSE1.1 KB
- NOTICE-PALATEKIT.md0.4 KB
- references/prompting-guide.md4.6 KB
- SKILL.md15.5 KB
Origin and licence
Modified by PalateKit
- Author
- jezweb
- Source
- github.com/jezweb/claude-skills/tree/1260fa7439b36b18dbf16648ccc7fb44783f6c23/plugins/design-assets/skills/ai-image-generator
- Licence
- MIT
Notice
Version modifiée de « ai-image-generator » (jezweb, MIT) : traduction française et fiche par PalateKit.
User reviews
–
No ratings yet
Loading reviews…
Frequently asked questions
How much does it cost?
Calls are billed by the provider. Gemini 2.5 Flash Image has a limited free tier. GPT Image 2 costs about $0.006 to $0.21 per image depending on quality.
Can I get a transparent background?
Yes, but only with GPT Image 1.5. GPT Image 2 and Gemini do not support transparency.