skills.rest
ViewWay
ViewWayCOMMUNITY
Explore all skills by this author →
GitHub

glmv-prompt-gen

Analyzes reference visuals to generate prompts for AI image and video tools via GLM-V vision API.

Updated Apr 2, 2026
Search Tags:#image-prompt#vision-analysis#prompt-generation#ai-art#language-detection#video-prompt
One-click install
npx skills add https://github.com/ViewWay/openclaw-skills --skill glmv-prompt-gen-viewway
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: glmv-prompt-gen
Source: https://github.com/ViewWay/openclaw-skills/tree/main/glmv-prompt-gen
Command: npx skills add https://github.com/ViewWay/openclaw-skills --skill glmv-prompt-gen-viewway

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

Analyze reference visuals (images or videos) to generate ready-to-use prompts for AI image and video generation tools, saving time and improving prompt quality.

Core Features & Use Cases

  • Analyze reference images and videos to produce prompts for both image and video generation tools (e.g., Midjourney, Stable Diffusion, DALL-E, Sora, Runway, Kling, Pika).
  • Automatically decide prompt language based on content (Chinese vs. English) and output cohesive prompts ready for copy-paste.
  • Supports input validation and clear error messages, with provision for using an API to derive prompts via GLM-V vision models.
  • Example: given a reference image, generate a cohesive prompt that captures subject, style, color palette, lighting, composition, and mood.

Quick Start

Provide a reference image or video and run the prompt generation script to produce ready-to-use prompts for image and video generation.

Frequently Asked Questions about glmv-prompt-gen

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AI image prompts from an existing reference visual?▼

To generate AI image prompts from a reference visual, provide the image or video to the script. The tool analyzes the subject, style, color palette, lighting, composition, and mood to produce a cohesive prompt ready for copy-paste.

Can I extract video prompts from reference visuals for Sora or Runway?▼

Yes, you can extract video prompts from reference visuals for tools like Sora, Runway, Kling, and Pika. The skill analyzes the input video to generate ready-to-use prompts tailored for video generation tasks.

Does the prompt generation tool support both English and Chinese output?▼

Yes, the prompt generation tool supports both English and Chinese output. It automatically detects the content language and decides the appropriate prompt language to ensure cohesive results for AI image and video generation.

What is the best way to create Midjourney prompts from an image?▼

The best way to create Midjourney prompts from an image is using a vision API to analyze the reference visual. This approach captures the visual elements and formats them into a structured prompt for Midjourney, Stable Diffusion, or DALL-E.

Why does my visual prompt extraction return an input validation error?▼

Visual prompt extraction returns an input validation error when the provided image or video format is unsupported or missing. The skill includes input handling and validation to ensure only valid reference visuals are processed by the GLM-V vision API.

What elements are included in a prompt generated from a reference image?▼

A prompt generated from a reference image includes the subject, style, color palette, lighting, composition, and mood. This structured output formatting ensures the generated prompt accurately captures the visual characteristics for AI art generation.

Related Skills

Explore More Design & Creative Skills→
ViewWayViewWay

glmv-grounding

Extract and visualize GLM-V grounding results from images or videos.

Community
Advanced
zai-orgzai-org
458

glmv-prompt-gen

Generate detailed text prompts from images and videos for AI synthesis.

Official
Intermediate
anavvanzinanavvanzin

agency-inclusive-visuals-specialist

Develop inclusive visual prompts with negative constraints and review checklists.

Community
Advanced
CyapstayeCyapstaye
9

baoyu-article-illustrator

Generate article illustrations by coordinating content analysis, prompt engineering, and image synthesis.

Community
Advanced