Stats
Actions
Tags
From image-gen
Use when the user wants to create, generate, or design a new image, artwork, illustration, diagram, icon, mockup, graphic, or visual from a text description using AI. Triggers on: generate image, create artwork, make an illustration, design a graphic, create a diagram, AI image, generate art, make a poster, create a logo concept, text-to-image, generate a picture, make me an image, create a visual, design an icon.
How this skill is triggered — by the user, by Claude, or both
Slash command
/image-gen:image-genThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate images from text descriptions using FAL AI's model ecosystem. Intelligently selects the
Generate images from text descriptions using FAL AI's model ecosystem. Intelligently selects the best model for the task, crafts optimized prompts, and delivers production-quality results.
See references/model-catalog.md for the full model catalog. Key models:
| Use Case | Default Model |
|---|---|
| Production quality | FLUX.2 [pro] or Seedream v4.5 |
| Highest quality | Nano Banana Pro or Imagen 4 Ultra |
| Fast drafts | FLUX.2 Flash or FLUX.2 [klein] |
| Text in images | Nano Banana Pro |
| Cinematic/aesthetic | Grok Imagine Image |
| Custom style (LoRA) | FLUX.2 [dev] LoRA |
Parse the user's request to extract:
If the request is vague, ask clarifying questions before proceeding.
Read references/model-catalog.md for the model selection decision tree.
If the user specifies a model, use it. Otherwise auto-select based on:
If reference/inspirational images are provided:
image-analyst agent to extract a style profilereferences/image-analysis.md for the analysis processprompt-architect agent with:
references/prompt-engineering.md for model-specific prompt strategiesreferences/text-to-image.md for the full T2I workflowreferences/fal-auth.md to verify FAL_KEY is setscripts/fal-submit.sh:./scripts/fal-submit.sh "{endpoint}" '{json_payload}' "./output/image-gen/{filename}"
references/text-to-image.mdreferences/output-delivery.md for output conventions./output/image-gen/)./output/image-gen/ with the standard naming conventionnpx claudepluginhub prakhar625/my-plugins --plugin image-genAI image generation and editing. Text-to-image, style transfer, and logo generation. Currently powered by Gemini and FLUX via OpenRouter. Triggers: generate image, create image, make image, draw, illustrate, logo, visual, picture.
Generates AI images from text prompts, edits images, and composes from multiple references using Gemini models. Supports t2i, i2i, product mockups, and stickers.
Generates and edits images via OpenRouter using FLUX and Gemini models. Use for photos, illustrations, artwork, and visual assets, not technical diagrams.