media-generation_skill

Overview

This skill generates high-quality images and videos using x402-protected AI models hosted at StableStudio. It supports text-to-image, text-to-video, image-to-video, and image editing workflows with cost/time tradeoffs between premium and budget models. Use it to produce final assets or fast drafts depending on project needs.

How this skill works

You send a POST request to a StableStudio x402 endpoint with a prompt and optional parameters (aspect ratio, size, duration). The API returns a jobId; poll the jobs endpoint until the job completes to retrieve imageUrl or videoUrl. For edits, upload or provide the source image URL, include it in the request, and the edit endpoint returns the modified asset.

When to use it

• Generate photoreal or stylized images from text prompts
• Produce short video clips from text or image inputs
• Edit or replace parts of an existing image using AI
• Create fast drafts with budget models before finalizing with premium models
• Automate visual content generation in pipelines or apps

Best practices

• Choose nano-banana-pro for best image quality and 2K–4K outputs; use nano-banana for fast budget drafts
• For videos, use veo-3.1 for higher quality and wan-2.5 for cost-sensitive use cases
• Poll jobs endpoint: check every ~3s for images and ~10s for videos to avoid wasted requests
• Specify aspectRatio and explicit size/duration to control outputs and costs
• Provide clear, specific prompts and include example image URLs for targeted edits

Example use cases

• Marketing teams generating multiple ad images at different aspect ratios and sizes
• Concept artists producing quick visual drafts with nano-banana, then refining with nano-banana-pro
• Social creators generating short motion clips (4–8s) using veo-3.1 for reels or stories
• Product teams automating image edits (background swaps, object removal) by uploading source images and sending edit prompts
• App developers integrating on-demand image/video generation into chatbots or content pipelines