image-generationCreate AI images with prompt engineering, style control, and provider guides for Midjourney, DALL-E, Stable Diffusion, Flux, and Leonardo.
Install via ClawdBot CLI:
clawdbot install ivangdavila/image-generationUser needs AI-generated images. Agent handles text-to-image, image editing, style transfer, upscaling, and provider selection.
User preferences persist in ~/image-generation/. See memory-template.md for setup.
~/image-generation/
āāā memory.md # Current provider, style, projects
āāā history.md # Past generations (optional)| Topic | File |
|-------|------|
| Memory setup | memory-template.md |
| Prompt techniques | prompting.md |
| API handling | api-patterns.md |
| OpenAI/DALL-E | openai.md |
| Midjourney | midjourney.md |
| Stable Diffusion | stable-diffusion.md |
| Flux | flux.md |
| Leonardo | leonardo.md |
| Ideogram | ideogram.md |
| Replicate | replicate.md |
Read ~/image-generation/memory.md for user's provider, preferred styles, and project context.
| Task | Best Provider |
|------|---------------|
| Photorealism | Midjourney, Flux Pro |
| Text in images | Ideogram, DALL-E 3 |
| Fast iteration | Flux Schnell, Leonardo |
| Maximum control | Stable Diffusion |
| Inpainting/editing | DALL-E 3, Stable Diffusion |
| Budget API | Replicate, Leonardo |
| Event | Action |
|-------|--------|
| User chooses provider | Save to memory.md |
| Style works well | Note in memory.md |
| New project started | Add to memory.md |
Data that leaves your machine:
Data that stays local:
~/image-generation/This skill does NOT:
~/image-generation/| Provider | Endpoint | Data Sent | Purpose |
|----------|----------|-----------|---------|
| OpenAI | api.openai.com | Prompt text | DALL-E generation |
| Midjourney | discord.com | Prompt text | Image generation |
| Stability AI | api.stability.ai | Prompt text | Stable Diffusion |
| Replicate | api.replicate.com | Prompt text | Flux, SD models |
| Leonardo | cloud.leonardo.ai | Prompt text | Leonardo generation |
| Ideogram | api.ideogram.ai | Prompt text | Text-in-image |
Endpoints depend on chosen provider. No other data is sent externally.
By using this skill, prompts are sent to third-party AI providers (OpenAI, Midjourney, Stability AI, etc.).
Only install if you trust these services with your prompts.
clawhub star image-generationclawhub syncGenerated Mar 1, 2026
Generate photorealistic product images for online stores, such as furniture in room settings or apparel on models, using providers like Midjourney or Flux for high-quality visuals. This reduces photoshoot costs and enables rapid iteration for A/B testing different styles.
Create custom images for social media ads, blog posts, or email newsletters with specific branding elements, leveraging DALL-E 3 or Ideogram for text integration. This speeds up content production and ensures visual consistency across campaigns.
Produce concept art for characters, environments, or items in video games, using Stable Diffusion for detailed control over styles and iterations. This accelerates the pre-production phase and allows for quick feedback loops with creative teams.
Generate illustrative images for textbooks, online courses, or presentations, such as historical scenes or scientific diagrams, with providers like Leonardo for fast iteration. This enhances engagement and reduces reliance on stock photography.
Create realistic renderings of building interiors or exteriors based on textual descriptions, using Midjourney for photorealism and specific lighting effects. This aids in client presentations and design validation before physical construction.
Offer a monthly subscription for businesses to access the skill with premium features like higher resolution outputs or priority support, generating recurring revenue. This model suits agencies needing consistent image generation for marketing or product development.
License the skill as an API for developers to integrate into their applications, charging per image generation request based on provider costs and complexity. This targets tech companies building custom solutions that require on-demand image creation.
Provide a free version with basic features and limited generations, then upsell to paid tiers for advanced providers like Flux Pro or higher usage limits. This attracts individual creators and small businesses, converting them to paying customers as needs grow.
š¬ Integration Tip
Integrate this skill by first setting up memory files to track user preferences, then use the provider selection rules to match tasks like photorealism or text-in-image generation for optimal results.
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Capture frames or clips from RTSP/ONVIF cameras.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation.
ä½æēØå ē½® image_generate.py čę¬ēęå¾ē, åå¤ęø ę°å ·ä½ē `prompt`ć
AI image generation powered by CellCog. Create images, edit photos, consistent characters, product photography, reference-based images, sets of images, style transfer. Professional image creation with AI.