Generate images from text and reference images via multiple AI APIs.
npx skills add https://github.com/lucasFR2/LogiSync --skill baoyu-image-gen-lucasfr2
Please help me install this Agent Skill. Skill: baoyu-image-gen Source: https://github.com/lucasFR2/LogiSync/tree/main/skills/baoyu-image-gen Command: npx skills add https://github.com/lucasFR2/LogiSync --skill baoyu-image-gen-lucasfr2
This Skill solves the problem of generating images using a variety of AI APIs, allowing users to create images based on text descriptions, reference images, aspect ratios, and batch generation from saved prompt files.
Use the baoyu-image-gen skill to generate an image of a cat in the style of a cartoon with the text "A cartoon cat" and reference image "cartoon.png".
High-intent search queries and answers about installing and using this skill.
To generate images from text descriptions, this Skill routes your prompts to various AI APIs including OpenAI, Google, and MiniMax. It functions as a centralized text-to-image interface, allowing you to create visual content without directly managing multiple API endpoints.
Yes, you can use reference images to guide AI image generation. The Skill accepts reference image inputs alongside text descriptions to direct the visual styling and composition, ensuring the generated output aligns with your provided reference assets.
Yes, you must provide your own API keys to generate images. The Skill requires access to AI APIs like OpenAI, Azure OpenAI, and Google, meaning you need to configure appropriate API keys within your environment.
You can generate multiple images in batch mode by utilizing saved prompt files. The Skill supports batch generation, allowing you to process numerous prompts sequentially through your selected AI APIs for efficient content creation.
The best way to generate AI images with specific aspect ratios for UI/UX design is to specify the desired dimensions within your text prompt. The Skill natively supports aspect ratio controls, ensuring outputs match your design requirements.
Yes, this text-to-image tool supports both DashScope and Z.AI GLM-Image APIs. It integrates with a wide variety of providers including OpenRouter, Jimeng, Seedream, and Replicate, giving you flexibility in choosing your generation engine.
archerliGenerates images from text prompts via multiple AI APIs.
doanchienthangdevOptimize, resize, convert, and batch process images with the Sharp library.
flashfoxerGenerate images from text or reference images via multiple AI APIs.
dp-archiveGenerate and edit images using Google Gemini's native image generation models.
