skills.rest
okbest2024
okbest2024COMMUNITY
Explore all skills by this author →
GitHub

autoglm-generate-image

Generate images from text prompts via the AutoGLM text-to-image API.

Updated Mar 18, 2026
Search Tags:#api#python#image-generation#text-to-image#ai-art#autoglm
One-click install
npx skills add https://github.com/okbest2024/openclaw-backup --skill autoglm-generate-image-okbest2024
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: autoglm-generate-image
Source: https://github.com/okbest2024/openclaw-backup/tree/main/workspace/skills/autoglm-generate-image
Command: npx skills add https://github.com/okbest2024/openclaw-backup --skill autoglm-generate-image-okbest2024

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

使用 AutoGLM 文生图接口，根据用户输入的文字描述生成图片。当用户需要生成图片、文字转图片、AI绘图等场景时使用此 skill。 Token 通过本地服务 http://127.0.0.1:53699/get_token 自动获取，无需手动配置环境变量。

Core Features & Use Cases

  • Text-to-image generation: 使用 AutoGLM API 根据描述生成图片，提升创作效率。
  • 本地令牌处理: 自动从本地服务获取 Bearer 令牌，简化认证流程。
  • 应用场景: 适用于概念美术、营销视觉、UI 原型等快速视觉化需求。

Quick Start

Run generate-image.py with a descriptive prompt to generate an image.

Frequently Asked Questions about autoglm-generate-image

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

FAQPage Schema
How do I generate images from text prompts using Python?▼

To generate images from text prompts using Python, this skill interfaces with the AutoGLM text-to-image API to create AI artwork directly from your descriptions. You simply run the generation script with a descriptive prompt to produce the visual output.

Do I need to manually configure API tokens for local text-to-image generation?▼

No, you do not need to manually configure API tokens for local text-to-image generation. The skill automatically retrieves the Bearer token from a local service at http://127.0.0.1:53699/get_token, completely simplifying the authentication process.

What prerequisites are needed to use the AutoGLM API for AI art creation?▼

To use the AutoGLM API for AI art creation, you must run a local token service at http://127.0.0.1:53699/get_token. The skill then uses signed HTTP headers with app id 100003 to authenticate requests to the endpoint.

Can I use text-to-image generation for UI prototypes and visual concepts?▼

Yes, you can use text-to-image generation for UI prototypes and visual concepts. The skill is specifically applicable for concept art creation, marketing visuals, and rapid visualization needs to improve creative efficiency.

How does the AutoGLM API authenticate HTTP requests for image generation?▼

The AutoGLM API authenticates HTTP requests for image generation by using signed HTTP headers. It specifically includes X-Auth-Appid, X-Auth-TimeStamp, and X-Auth-Sign headers, utilizing app id 100003 to validate the endpoint requests.

Related Skills

Explore More Design & Creative Skills→
okbest2024okbest2024

autoglm-open-link

Fetch complete webpage text content via the AutoGLM Open Link API.

Community
Advanced
SeongHuniSeongHuni

reverse-document

Parse game system source code to generate markdown design documentation.

Community
Advanced
dracohu2025-clouddracohu2025-cloud
225

nano-banana-image

Generates images via Nano Banana 2/Gemini 3.1 Flash Image using OpenRouter and Python scripts.

Community
Intermediate
234194027-cpu234194027-cpu

autoglm-image-recognition

Converts images to natural-language descriptions via AutoGLM Image Recognition API.

Community
Basic