Generate images from text prompts using the MiniSearch API.
npx skills add https://github.com/qq5855144/GitHubM --skill minimax-text-to-image
Please help me install this Agent Skill. Skill: minimax-text-to-image Source: https://github.com/qq5855144/GitHubM/tree/main/.skills/minimax-text-to-image Command: npx skills add https://github.com/qq5855144/GitHubM --skill minimax-text-to-image
This Skill removes the manual effort of creating images from scratch by turning natural-language prompts into generated visuals with a production-ready workflow for retrieval and storage.
Describe the image you want, specify any style or aspect ratio preferences, and ask this skill to generate the images and return usable links.
High-intent search queries and answers about installing and using this skill.
To generate images from text prompts, describe the visual you need and specify any style or aspect ratio preferences. The Skill uses the MiniMax API to convert natural-language prompts into polished visuals suitable for posters, concepts, and app mockups.
Yes, you can batch generate multiple images at once. The workflow supports specifying standard aspect ratios or custom sizes, allowing you to produce several variations of a concept simultaneously and handle outputs as URLs or base64.
Yes, it supports the image-01 model for flexible generation and the image-01-live model for style-guided, more realistic outputs. This allows you to choose between versatile creative generation and producing stylized, lifelike assets.
To persist temporary image URLs, the Skill transfers generated links into durable storage like Supabase. This persistent delivery mechanism ensures your generated creative assets remain accessible for immediate review after the initial generation.
The best way to automate concept art generation is using a prompt-to-image workflow that removes manual effort. By describing a scene like a cinematic product shot, you can generate multiple variations and save the resulting assets directly.
SheshiyerGenerate Gemini 3.1 flash image previews from prompts via the inference.sh CLI.
epoko77-aiValidate AI-generated design assets against baselines using a 5-axis scoring rubric.
CENKSSSCoordinate QE agents to automate test generation and quality gates.
sixtycat2000-ctrlGenerate AI images via Volcengine Seedream with text-to-image and editing.
