stability-aiGenerate high-quality images via Stability AI API (SDXL, SD3, Stable Image Core). Use when user asks to "generate image", "make a picture", or "draw this".
Install via ClawdBot CLI:
clawdbot install 1999AZZAR/stability-ai.env.example to .env.STABILITY_API_KEY in .env.API_HOST if using a custom endpoint.(The script automatically handles dependencies on first run)
# Basic generation
scripts/generate "A futuristic city with neon lights"
# Aspect ratio (1:1, 16:9, 9:16, 21:9, 4:3, 3:4)
scripts/generate "Landscape painting" --ratio 16:9
# Style preset
scripts/generate "Portrait of a warrior" --style photographic
# Seed for reproducibility
scripts/generate "Abstract art" --seed 42
# Negative prompt
scripts/generate "Beautiful sunset" --negative "blurry, low quality"
# Output format (png, jpg, webp)
scripts/generate "Nature scene" --format webp
# Advanced: Custom model, steps, CFG scale
scripts/generate "Fantasy landscape" \
--model stable-diffusion-3-medium \
--steps 50 \
--cfg 7.0 \
--ratio 21:9
# V2 API (experimental)
scripts/generate "Modern architecture" --v2
# Combined options
scripts/generate "Cyberpunk street at night" \
--ratio 16:9 \
--style neon-punk \
--seed 123 \
--format jpg \
--steps 45 \
--cfg 6.5
Available styles: enhance, anime, photographic, digital-art, comic-book, fantasy-art, line-art, analog-film, neon-punk, isometric, low-poly, origami, modeling-compound, cinematic, 3d-model, pixel-art, tile-texture
Supported: 1:1 (default), 16:9, 9:16, 21:9, 4:3, 3:4
Each generated image includes a JSON metadata file with:
stable-diffusion-xl-1024-v1-0)references/models.md for complete model list, API versions, and credit costs.Automatically keeps the last 20 generated images. Older files and their metadata are removed to save disk space.
Generated Mar 1, 2026
Marketing teams can use this skill to quickly generate custom visuals for campaigns, social media posts, and advertisements. It supports various aspect ratios like 16:9 for videos and 1:1 for social media, with style presets like cinematic or photographic to match brand aesthetics.
Game developers can create concept art, character designs, and environment textures using style presets like fantasy-art or pixel-art. The ability to set seeds ensures consistency for iterative design, while auto-cleanup manages storage by keeping only recent files.
Online retailers can generate product mockups or lifestyle images to showcase items in different settings, using photographic or digital-art styles. Features like negative prompts help avoid unwanted elements, and output formats like WebP optimize images for fast loading on websites.
Educators and content creators can produce illustrations for textbooks, presentations, or online courses, leveraging styles like line-art or isometric for clarity. The metadata tracking aids in documenting sources, and aspect ratios like 4:3 suit traditional slide formats.
Architects and designers can generate realistic renderings of buildings or interiors using the photographic style and custom models like SD3. Advanced options like steps and CFG scale allow fine-tuning for detailed outputs, with 21:9 ratios for panoramic views.
Offer a free tier with limited generations per month to attract individual creators, then charge for higher limits, priority processing, or access to premium models like SD3. Revenue comes from subscription fees, with tiered plans based on usage and features.
License the skill to software companies or platforms (e.g., design tools or CMS) for embedding image generation capabilities. Charge upfront licensing fees or revenue-sharing based on user transactions, leveraging the skill's easy setup and command-line interface.
Provide managed services where businesses outsource image generation for specific projects, such as ad campaigns or product catalogs. Use the skill's batch capabilities and style presets to deliver high volumes efficiently, charging per project or on a retainer basis.
đŹ Integration Tip
Ensure the STABILITY_API_KEY is securely stored in environment variables and test the API host configuration for custom deployments to avoid downtime.
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.
äœżçšć çœź image_generate.py èæŹçæćŸç, ć〿ž æ°ć ·äœç `prompt`ă
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.