Generate images from text prompts via the GLM-Image API.
npx skills add https://github.com/zai-org/GLM-skills --skill glm-image-gen
Please help me install this Agent Skill. Skill: glm-image-gen Source: https://github.com/zai-org/GLM-skills/tree/main/skills/glm-image-gen Command: npx skills add https://github.com/zai-org/GLM-skills --skill glm-image-gen
Converts natural-language descriptions into high-quality visual assets so users don't need manual image editing or specialist design skills to produce illustrations, portraits, social graphics, or posters.
Generate an HD 1280x1280 image of "a smiling elderly scientist holding a vintage microscope, watercolor style, soft natural lighting" using the glm-image model.
High-intent search queries and answers about installing and using this skill.
To generate images from text prompts via CLI, provide prompt, model, size, and quality parameters to the GLM-Image API. The process requires a ZHIPU_API_KEY for authentication and returns temporary image URLs with content filtering metadata.
Yes, you can control watermarks and aspect ratios during AI art generation. The system enforces dimension rules for supported models and includes watermark control parameters to ensure your output meets specific visual requirements.
Yes, a ZHIPU_API_KEY is required for authentication to use text-to-image generation. Without this key, the CLI cannot validate your requests or return generated images from the GLM-Image API.
For social media graphics and posters, the system supports HD and standard quality options with multiple aspect ratios. It validates dimension rules specific to the glm-image model to prevent invalid requests before processing your prompt.
Text-to-image requests return content filtering metadata because the API performs safety checks during generation. This metadata accompanies your temporary image URLs to indicate if the prompt or output triggered any moderation filters.
Yes, you can save generated images locally. The CLI workflow supports optional local file saving for downstream use, alongside returning temporary image URLs and content filtering results from the API response.
archibateGenerate images from text prompts via Z.ai's glm-image endpoint.
pragyaP17Scrape webpage content, extract metadata, download images, and prepare for AEM Edge Delivery Services import.
cellarwoodSanitize user prompts via a Model Armor template using CLI inputs.
haboshiGenerate and edit images with Google Gemini, OpenAI GPT Image, and ZhipuAI GLM-Image.
