AI & MLOfficial★ 6.3k
Image Generation — Create Visuals from Text
Generate and edit images using DALL·E, Stable Diffusion, or FLUX. Create diagrams, illustrations, social media graphics, and concept art — all via natural language.
Visual Creation at Your Command
OpenClaw's built-in image generation tool supports multiple providers. Generate anything from quick social media graphics to detailed concept art — all through natural conversation.
- Multi-Provider: DALL·E 3, Stable Diffusion XL, FLUX.1, and more.
- Image Editing: Modify existing images with text instructions (inpainting, outpainting).
- Batch Generation: Create multiple variations and choose the best.
- Auto-Save: Generated images are saved to your workspace automatically.
Configuration
// openclaw.json — image generation is built-in
{
"tools": {
"image_generate": {
"enabled": true,
"provider": "openai",
"model": "dall-e-3"
}
}
}Top Prompts
- "Generate a professional logo for a tech startup called NeuralFlow."
- "Create a social media banner for our product launch."
- "Generate a system architecture diagram for a microservices app."
</ Add to your README
If you use this skill in your project, add the badge to your GitHub README:
[](https://clawdbot.space/en/skills/image-generation?ref=badge&utm_source=image-generation&utm_medium=readme&utm_campaign=skill-page)