Generate images from text prompts via the GLM-Image API.
npx skills add https://github.com/ViewWay/openclaw-skills --skill glm-image-gen-viewway
Please help me install this Agent Skill. Skill: glm-image-gen Source: https://github.com/ViewWay/openclaw-skills/tree/main/glm-image-gen Command: npx skills add https://github.com/ViewWay/openclaw-skills --skill glm-image-gen-viewway
This skill enables users to generate professional visuals by turning text prompts into high-quality images via the ZhiPu GLM-Image API. It supports scientific illustrations, portraits, social media graphics, and posters, with multiple aspect ratios and watermark controls.
Invoke the glm-image-gen CLI to generate an image from a prompt like "a futuristic city skyline at dusk" using default HD quality.
High-intent search queries and answers about installing and using this skill.
To generate images from text prompts via an API, you provide a descriptive text string to the GLM-Image API. It processes your input and returns high-quality visuals suitable for scientific illustrations, portraits, or posters.
You need a valid ZHIPU_API key to use the GLM-Image API for image generation. The CLI enforces model, size, and safety validations, requiring this key to authenticate your requests and generate visuals.
You can control aspect ratios and watermarks when generating images from text. The generation process supports multiple aspect ratios for various graphics and includes options to apply watermarks for content protection.
The best way to create AI artwork and marketing visuals from text descriptions is using a CLI that interfaces with the GLM-Image API. It handles content-safety validations and outputs HD-quality graphics.
Text prompt image generation enforces content-safety validations to ensure generated visuals comply with platform policies. The CLI checks prompts against safety rules before processing requests through the API.
The image generation CLI supports scientific illustrations and social media graphics. It translates text prompts into high-quality images across multiple aspect ratios, accommodating diverse design and creative needs.
Abdullahmohammadareftest1
se1111thGenerate images, videos, and stock images from textual prompts.
Quill-AgentGenerate images from text prompts using the Stable Diffusion model.
feed-mobConvert prompts and images into Gemini image generation API calls.
