freeimg-z-image

freeimg-z-image is a skill for Claude Code, Codex from wu529778790/shenzjd-skills. It costs 164 tokens per session (1,541 once invoked), scanned B, original, MIT.

A text-to-image tool that sends prompts to the free z-image-turbo model and saves the results as PNG files. It supports negative prompts, image size choices, and generation-step settings.

In plain words
What is it for?
Use it for icons, covers, illustrations, posters, avatars, and other images described in text. It does not edit an existing image.
Why use it?
It lets you create new images without paying for an image API, after a one-time free-token setup.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for icons, covers, illustrations, posters, avatars, and other images described in text. It does not edit an existing image.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wu529778790/shenzjd-skills/freeimg-z-image
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add wu529778790/shenzjd-skills --skill freeimg-z-image
Clone the repo
git clone --depth 1 https://github.com/wu529778790/shenzjd-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for freeimg-z-image

README.md
[![agentmods](https://agentmods.dev/badge/skills/wu529778790/shenzjd-skills/freeimg-z-image/github.svg)](https://agentmods.dev/skills/wu529778790/shenzjd-skills/freeimg-z-image)
Your own site
<a href="https://agentmods.dev/skills/wu529778790/shenzjd-skills/freeimg-z-image"><img src="https://agentmods.dev/badge/skills/wu529778790/shenzjd-skills/freeimg-z-image/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for freeimg-z-image

Your own site · 80×15
<a href="https://agentmods.dev/skills/wu529778790/shenzjd-skills/freeimg-z-image"><img src="https://agentmods.dev/badge/skills/wu529778790/shenzjd-skills/freeimg-z-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,541 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00164 $0.01541
Opus 5.5 $0.00066 $0.00616
Sonnet 5.5 $0.00033 $0.00308
Haiku 4.5 $0.00016 $0.00154

Measured 1mo ago against content hash 0460374f1f11, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

freeimg-z-image scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

把令牌写入 `~/.freeimg-z-image/config.env`(`chmod 600`),只需一次。
freeimg-z-image/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FreeImg Z-Image — 免费 AI 图片生成

把一句话提示词变成 2K 高清图片:底层调用 Gitee AI Serverless API 的 z-image-turbo 模型(8 步极速生成),每天约 100 张免费额度,只需一个 免费令牌。不依赖任何付费服务。

可视化网页版:freeimg.shenzjd.com —— 不想写提示词时直接用网页版:内置 18000+ 精选提示词库、12 种预设 风格(公众号封面 / 小红书封面 / 知识卡片 / 海报 / 3D 卡通 / 中国风等)、 7 种尺寸比例、历史记录与图床上传。Skill 负责让 AI 在对话里直接出图, 网页版负责人工精修与逛提示词库,两者共用同一款令牌。

When to Use

  • User asks to generate / draw / create an image (icon, cover, illustration, poster, avatar)
  • User mentions 文生图 / 画图 / 生成图片 / AI 绘画 / 生成头像 / 生成封面
  • User wants quick AI images without paid API keys (z-image-turbo is free)

When NOT to Use:

  • User wants to edit an existing image (this skill is text-to-image only) — for 垫图/图生图 use the freeimg-hunyuan skill
  • User explicitly needs the Hunyuan/混元 model or the WeChat 小程序成长计划 free quota — use the freeimg-hunyuan skill
  • User explicitly needs another model (DALL·E, Midjourney, Flux…) — use the corresponding skill/API
  • No network access or Gitee AI is unreachable

Core Pattern

Step 0: 首次使用 — 配置免费令牌

令牌获取(免费,三步,详见 freeimg.shenzjd.com 页面教程): 登录 ai.gitee.com/serverless-api → 任意模型详情页点「在线体验」→「API」→「添加令牌」→ 复制。

脚本按以下优先级读取令牌(不要把令牌写进仓库、日志或对话输出):

  1. 环境变量 GITEE_AI_API_KEY
  2. 本地配置文件 ~/.freeimg-z-image/config.env(内容一行:GITEE_AI_API_KEY=xxxx)

都没有时脚本会打印上面的获取引导并退出;AI 应引导用户完成 Step 0, 把令牌写入 ~/.freeimg-z-image/config.env(chmod 600),只需一次。

Step 1: 生成图片

scripts/generate.mjs --prompt "提示词" --out 输出.png \
  [--width 1024] [--height 1024] [--steps 8] [--negative "负向提示词"]
  • --width/--height:必须为 8 的倍数;常用组合见 Quick Reference
  • --steps:默认 8(turbo 模型推荐值,越高越慢)
  • --negative:不传时默认 文字,字母,水印,签名,模糊
  • 接口偶发 502,脚本已内置 2 次退避重试;仍失败则换时间再试

Step 2: 交付

  • 生成后先查看图片(Read 工具)确认质量,再交给用户;不满意就换提示词重新生成,不要把废图丢给用户
  • 需要小尺寸(如 App 头像 144×144)时用 sips -Z 144 原图 --out 小图.png(macOS)或 ImageMagick convert -resize 缩放
  • 提示词用中文即可,模型中文理解良好;结构:风格 + 主体 + 细节 + 构图 + 无文字无水印

Read the full file on GitHub · 88 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 88 lines · 164 tokens per session scan B 0460374f1f11

Subscribe to this mod's changes

freeimg-z-image is a skill published in the GitHub repository wu529778790/shenzjd-skills (3 stars, last pushed 28d ago), licensed MIT. It adds 164 tokens to every session and 1,541 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-16.