Image Gen (Gemini)

Generate high-quality images and edit existing ones using Google's Gemini image generation models — directly in your Clawly conversations.

What You Can Do

• Generate images from text descriptions
• Edit and transform existing images
• Create illustrations, mockups, and visuals
• Iterate on image styles and compositions
• Generate images for marketing, social media, and presentations

Example Commands

"Generate an image of a minimalist workspace with a laptop and a plant"

"Create a hero illustration for a SaaS landing page, blue and white"

"Generate a product mockup for a mobile app"

"Make an image of a friendly AI robot waving hello"

"Create a banner image for a newsletter about productivity"

Setup

1. Get a Google Gemini API Key

1. Go to aistudio.google.com
2. Sign in with your Google account
3. Click Get API key
4. Create a new API key or copy an existing one
5. Ensure the Gemini API is enabled in your project

2. Add to Clawly

1. Go to your Clawly Dashboard
2. Find Image Gen (Gemini) in the Skills section
3. Click Configure
4. Paste your Gemini API Key
5. Click Save

How It Works

1. Prompt processing — Clawly refines your description for the best results
2. Image generation — Sends the prompt to Gemini's image model
3. Delivery — Returns the generated image directly in the conversation

Tips

• Describe style — "Minimalist," "photorealistic," "cartoon style," or "watercolor" improves results
• Specify dimensions — "Wide banner," "square icon," or "portrait" sets the format
• Iterate — Ask for variations: "Make it darker" or "add a mountain in the background"

Pricing

Gemini API pricing depends on your Google AI usage plan. Check the Google AI Pricing page for current rates.

Need help? Contact us at support@getclawly.com