Generate images from text prompts and reference images via multiple provider APIs.
npx skills add https://github.com/ginobefun/gino-skills --skill image-gen-ginobefun
Please help me install this Agent Skill. Skill: image-gen Source: https://github.com/ginobefun/gino-skills/tree/main/skills/image-gen Command: npx skills add https://github.com/ginobefun/gino-skills --skill image-gen-ginobefun
Provide a unified, production-ready interface to generate and edit images using multiple provider APIs, removing the overhead of handling provider-specific APIs, model selection, aspect ratios, reference-image edits, and environment configuration for everyday creative and automation tasks.
Generate a 2k landscape image of a golden retriever running on a beach and save it as out.png using the Google provider.
High-intent search queries and answers about installing and using this skill.
To generate images from text prompts using multiple AI providers, you can use a unified interface that connects to Google, OpenAI, DashScope, and Replicate. This approach removes the overhead of handling provider-specific APIs for everyday creative and automation tasks.
Yes, you can perform reference-based edits using multimodal reference images. When reference images are supplied, the system supports multimodal editing if the provider or model allows it, including automatic provider selection for Gemini.
You can control aspect ratio, size, and quality presets by using explicit imageSize commands, preset quality mappings like normal or 2k, and aspect ratio mappings. The system applies sensible defaults and fallbacks for your specified parameters.
Yes, the image generation tool supports optional parallel batch generation for creating multiple images at once. It also includes R2 upload utilities, automatically handling provider detection and retrying transient failures during the batch process.
Yes, you need to configure environment variables and complete a first-time EXTEND.md preference setup before generation. The system resolves models from CLI flags, EXTEND.md, and environment variables, then displays the chosen provider and model.
The best way to handle provider-specific API differences is using a production-ready interface that standardizes provider detection and model resolution across Google, OpenAI, DashScope, and Replicate, enforcing operational safety with automatic retries.
JaylaelikeSet up Auth.js v5 authentication in Next.js with Google OAuth and credentials provider.
bitwize-music-studioUpload promo videos and album content to Cloudflare R2 or AWS S3.
GarrettRoiDelegate coding tasks to the OpenAI Codex CLI agent within a git repository.
guanyangGenerate images across multiple AI providers from a single prompt.
