Lewati ke konten
TakoAPI
Kembali ke skill

zhipu-cogview-image

oleh honestqiao

Image & Video Generation
—Belum ada penilaian
Penilaian Anda

Ringkasan

Generate images using Zhipu AI's CogView model.

Deskripsi

Apa yang Dilakukan Skill Ini

Generates images from text prompts using Zhipu AI's CogView-4 model via API calls. Requires a Zhipu AI API key and communicates over HTTPS with input validation and JSON escaping built in.

Uses CogView-4, a model specifically trained on Chinese-language and culturally relevant content, making it more suitable than Western alternatives for prompts involving Chinese aesthetics or subjects.

Kapan Menggunakannya

  • Generate illustrations from text descriptions
  • Create concept art for a project
  • Produce reference images for design work
  • Generate images of specific scenes or characters
  • Quickly prototype visual ideas without design tools

Contoh Alur Kerja

INPUT

User asks: Generate an image of a mountain village at sunset

AGENT
  1. 1

    Set ZHIPU_API_KEY environment variable

  2. 2

    Construct JSON payload with model cogview-4 and the prompt

  3. 3

    Send POST request to Zhipu AI images/generations endpoint via curl

  4. 4

    Parse response with jq to extract image URL

OUTPUT

A URL pointing to the generated image of a mountain village at sunset

Persyaratan

  • ZHIPU_API_KEY environment variable
  • Zhipu AI account at bigmodel.cn

Instalasi

clawhub install honestqiao/zhipu-cogview-image

Jalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.

Tautan