image-generation
AI-powered image generation and editing using Google Gemini and OpenAI DALL-E models.Generate images from text descriptions, edit existing images, create logos/stickers,apply style transfers, and produce product mockups.Use this skill when the user requests:- Image generation from text descriptions- Image editing or modifications- Logos, stickers, or graphic design assets- Product mockups or visualizations- Style transfers or artistic effects- Iterative image refinementAvailable models: gemini-2
Security Assessment
Detected risks:
About image-generation
The image-generation skill is designed to facilitate AI-powered image creation and editing by leveraging advanced models from Google and OpenAI. It addresses the need for high-quality, customized images generated from natural language descriptions, enabling users to create everything from photorealistic images to artistic illustrations, logos, and product mockups. Whether it's designing logos, generating visual content for marketing, or editing images with specific adjustments, this skill provides the tools to meet diverse visual creation needs.
FAQ
How do I generate images using this skill?
To generate images, simply provide a text description of the image you want to create, such as 'create a logo for a coffee shop' or 'generate an image of a mountain sunset.' The skill will use the appropriate AI model to generate the requested image.
Which AI models are available in this skill?
This skill uses several models, including Google Gemini (e.g., gemini-2.5-flash-image and gemini-3-pro-image-preview), Google Imagen (e.g., imagen-4.0-fast-generate-001 and imagen-4.0-generate-001), and OpenAI (e.g., gpt-image-1.5 and dall-e-3). Each model offers unique features based on quality, speed, and complexity.
Can I edit existing images with this skill?
Yes, you can edit existing images by providing text instructions on the desired changes. For example, 'change the background to a beach' or 'add a person to the image.' The skill will modify the image based on your specifications.
Are there any specific requirements for using this skill?
This skill requires access to the image generation models (Google Gemini, Google Imagen, or OpenAI), and it works best for users looking to generate or edit images at various levels of detail. Ensure you are familiar with the model's capabilities, as certain models excel in specific tasks like speed or photorealism.
Install image-generation
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
jkitchin/skillz