videoagent-image-studio_skill

Overview

This skill gives one-command access to eight state-of-the-art image generation models so you can create photos, illustrations, icons, logos, and more without managing API keys. It automatically selects the best model for the job or lets you pick a specific engine for style, speed, or format. Results are returned as stable image URLs in a unified response shape for easy delivery to users.

How this skill works

The skill routes requests through a hosted proxy that handles authentication and model orchestration, so no API keys are required by the caller. You provide a prompt (optionally enhanced with style, lighting, and quality descriptors) and the selected model generates images; the script waits for completion and returns imageUrl and images arrays. Midjourney-specific flows (grids, upscales, variations) are supported with simple action commands and the same unified output format.

When to use it

• User asks to generate any image, photo, illustration, icon, logo, or artwork
• You want quick drafts and fast iteration without key management
• You need model-specific strengths (cinematic art, photorealism, vector icons, anime)
• You want consistent outputs with optional reference images or reproducible seeds

Best practices

• Enhance prompts with model-appropriate descriptors (lighting, detail, camera terms) before sending
• Pick model by intent: midjourney for cinematic/artistic, flux-pro for photorealistic product shots, recraft for vector/icon work
• Use aspect-ratio and num-images to control framing and batch size; Midjourney always returns a 4-image grid
• For Midjourney, offer users upscale/variation/reroll options after the initial grid
• Provide negative-prompts or seeds when reproducibility or avoidance is important

Example use cases

• Generate a cinematic snow leopard scene with Midjourney-style descriptors and return four options for user selection
• Create a photorealistic perfume product shot with flux-pro for marketing assets
• Produce a quick app icon in flat, vector style using recraft and return a single PNG/SVG URL
• Make a poster with text using ideogram and explicit font/layout instructions
• Iterate fast on concepts using flux-schnell to get near-instant previews