skills.rest
zhangyanbo2007
zhangyanbo2007COMMUNITY
Explore all skills by this author →
GitHub

image-gen

Generate and edit images from text prompts or reference images via API.

Updated Apr 7, 2026
Search Tags:#workspace#compression#image-generation#feishu#image-editing#ai-art
One-click install
npx skills add https://github.com/zhangyanbo2007/openclaw --skill image-gen-zhangyanbo2007
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-gen
Source: https://github.com/zhangyanbo2007/openclaw/tree/main/workspace/skills/image-gen-skill
Command: npx skills add https://github.com/zhangyanbo2007/openclaw --skill image-gen-zhangyanbo2007

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Pillow, jq, curl.

What problem does it solve?

This Skill automates AI-powered image generation and editing from text prompts or reference images, saving time and reducing manual image processing, while ensuring large outputs are compressed and stored locally for quick access and sharing.

Core Features & Use Cases

  • Text-to-image and image-to-image generation using a Nano-banana API.
  • Automatic compression of images larger than 1MB, saved under ~/.openclaw/workspace/img.
  • Feishu integration to display generated images directly in chats.
  • Use cases include rapidly creating illustrations for products, marketing visuals, and design concepts.

Quick Start

Provide a text prompt or a reference image to generate an image, which will be automatically compressed when needed and saved to the workspace for Feishu display.

Frequently Asked Questions about image-gen

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

FAQPage Schema
How do I generate images from text prompts and compress them for Feishu?▼

AI image generation from text prompts produces visual assets automatically compressed over 1MB using Pillow. Generated images save locally to the workspace for Feishu-ready sharing.

How does image-to-image editing work with a reference image?▼

Image-to-image editing transforms a provided reference image using AI processing via the Nano-banana API. The output is compressed if large and stored under the workspace directory.

Do I need a local .env file to run image generation workflows?▼

A local .env file is required for image generation workflows, specifying IMAGE_API_BASE_URL, IMAGE_API_KEY, and optional IMAGE_MODEL, IMAGE_SIZE, IMAGE_ASPECT_RATIO for API requests.

Can I use curl and jq to construct image generation API requests?▼

Curl and jq are required dependencies to construct and manage API requests for AI image generation. They handle the HTTP communication and JSON parsing for the Nano-banana API.

What is the best way to compress generated images larger than 1MB?▼

Automatic compression of images larger than 1MB is handled natively using the Pillow library. Compressed files are saved directly to the workspace path for quick local access.

Are there limitations when generating AI illustrations for marketing visuals?▼

AI illustration generation depends on external API availability and configured environment variables. Large outputs are compressed automatically, which may affect final image resolution.

Related Skills

Explore More Design & Creative Skills→
SatangThevalueSatangThevalue

gif-search

Search and download GIFs from Tenor using curl and jq.

Community
Intermediate
autogame-17autogame-17
20

Feishu Image Skill

Upload and send images to Feishu chats with cached image keys.

Community
Intermediate
tentacle-protentacle-pro
4

baoyu-article-illustrator

Analyze articles to generate structured illustration prompts and image assets.

Community
Advanced
JoeyJoziahJoeyJoziah

nano-banana-pro

Generate and edit images from natural-language prompts using Gemini 3 Pro Image.

Community
Intermediate