Generate detailed text prompts from images and videos for AI synthesis.
npx skills add https://github.com/zai-org/GLM-skills --skill glmv-prompt-gen
Please help me install this Agent Skill. Skill: glmv-prompt-gen Source: https://github.com/zai-org/GLM-skills/tree/main/skills/glmv-prompt-gen Command: npx skills add https://github.com/zai-org/GLM-skills --skill glmv-prompt-gen
Converting reference images or video clips into high-quality, ready-to-use prompts for text-to-image and text-to-video generators is time-consuming and requires prompt engineering skill. This Skill automates visual analysis and crafts detailed prompts that capture subject, style, lighting, composition, and mood so creators can reproduce or remix visuals quickly.
Ask the skill to analyze this image URL and produce a copy-paste-ready prompt for Midjourney that describes the subject, style, lighting, composition, color palette, and mood.
High-intent search queries and answers about installing and using this skill.
To generate Midjourney prompts from an image, this Skill analyzes visual elements like subject, style, and lighting to automatically produce copy-paste-ready text prompts for text-to-image synthesis workflows.
Yes, you can extract Stable Diffusion prompts from a video URL. The auto mode analyzes video content to capture atmosphere and composition, generating detailed prompts for text-to-video or text-to-image generation.
Yes, a ZHIPU_API_KEY is required. This Skill uses the key to access GLM-V models, which perform the underlying visual analysis needed to extract subjects and styles for your generated prompts.
The prompt generator supports both Chinese and English outputs. It automatically selects the appropriate language based on visual cues and any text detected within the provided reference images or video clips.
The best way to convert a reference photo into a text-to-video prompt is using the image or auto mode, which breaks down lighting and mood to craft tailored prompts for video synthesis tools like Runway.
You can use local base64 images for prompt engineering by passing them to the Python script. The system validates the input and extracts visual details to produce polished, ready-to-use AI art prompts.
zai-orgGenerate captions and summaries for images, videos, and documents via the GLM-V API.
vuminhieuCraft structured prompts for AI text and image generation tasks.
JylhisIntegrate Claude API capabilities into applications across multiple programming languages.
archibateGenerate images from text prompts via Z.ai's glm-image endpoint.
