Generate AI images with DALL-E - create images from text descriptions, edit existing images, and manage creations
Enables Claude to use OpenAI's DALL-E for AI image generation through ChatGPT's interface, including creating images from descriptions, editing images, and managing generated content.
curl -sSL https://canifi.com/skills/dall-e/install.sh | bash
Or manually:
cp -r skills/dall-e ~/.canifi/skills/
Configure via canifi-env:
# First, ensure canifi-env is installed:
# curl -sSL https://canifi.com/install.sh | bash
canifi-env set OPENAI_EMAIL "[email protected]"
canifi-env set OPENAI_PASSWORD "your-password"
Your credentials, your choice. Canifi LifeOS respects your privacy.
If you prefer not to share credentials with Claude Code:
If you're comfortable sharing credentials, you can store them locally:
canifi-env set SERVICE_EMAIL "your-email"
canifi-env set SERVICE_PASSWORD "your-password"
Note: Credentials stored in canifi-env are only accessible locally on your machine and are never transmitted.
User: "Create a DALL-E image of a cozy coffee shop interior"
Claude: I'll generate that image.
1. Opening ChatGPT via Playwright MCP
2. Activating DALL-E image generation
3. Entering prompt: "cozy coffee shop interior, warm lighting"
4. Waiting for image generation
5. Displaying and offering download
User: "Edit my image to add a cat sitting in the corner"
Claude: I'll edit your image.
1. Uploading your image to DALL-E
2. Specifying edit region
3. Adding prompt: "add a cat sitting in the corner"
4. Processing the edit
5. Showing the modified result
User: "Generate 4 different logo concepts for a tech startup"
Claude: I'll create logo variations.
1. Crafting detailed logo prompt
2. Generating first concept
3. Creating variations with different styles
4. Compiling all 4 concepts for review
When DALL-E or ChatGPT updates: