freeimg-hunyuan

freeimg-hunyuan is a skill for Claude Code, Codex from wu529778790/shenzjd-skills. It costs 246 tokens per session (1,840 once invoked), scanned B, original, MIT.

An image-generation tool using Tencent’s Hunyuan 3.0 model, supporting both text-to-image creation and image-to-image editing with a reference image. It uses Tencent Cloud credentials and a configured CloudBase environment.

In plain words
What is it for?
Use it for illustrations, covers, avatars, and other generated images, including edits based on a supplied reference image.
Why use it?
It provides a way to create or modify images using a free Tencent resource allocation when that allocation has been claimed and configured.

Skill for Claude CodeCodex

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

Good fit Use it for illustrations, covers, avatars, and other generated images, including edits based on a supplied reference image.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/wu529778790/shenzjd-skills/freeimg-hunyuan"><img src="https://agentmods.dev/badge/skills/wu529778790/shenzjd-skills/freeimg-hunyuan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 246 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,840 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 $0.00246 $0.01840
Opus 5.5 $0.00098 $0.00736
Sonnet 5.5 $0.00049 $0.00368
Haiku 4.5 $0.00025 $0.00184

Measured 1mo ago against content hash 68d2b503e0b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

freeimg-hunyuan 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.

mkdir -p ~/.freeimg-hunyuan && printf "TCB_ENV_ID=你的环境ID\nTCB_SECRET_ID=你的SecretId\nTCB_SECRET_KEY=你的SecretKey\n" > ~/.freeimg-hunyuan/config.env && chmod 600 ~/.freeimg-hunyuan/config.env
freeimg-hunyuan/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FreeImg Hunyuan — 腾讯混元生图(免费 10 万张额度)

调用腾讯云混元 3.0 生图模型(走 CloudBase AI 网关),支持文生图与垫图 (图生图)。完全免费,不花一分钱:额度来自微信「小程序成长计划」激励 资源包——10 万张 AI 生图 + 10 亿 Token,全行业开发者免费领取,6 个月有效, 额度烧在你自己云开发环境的资源包上。

可视化网页版 + 图文教程:freeimg.shenzjd.com/hunyuan —— 网页里有从领取资源包、创建密钥到出图的完整备注教程(Step 0 卡片式引导), 不想配本地环境时在网页上填密钥即用,两者共用同一套腾讯云凭据。

When to Use

  • User 明确要混元 / Hunyuan / 腾讯云出图,或需要垫图(参考图改图)
  • User 走微信小程序生态、想用「小程序成长计划」激励资源包的10 万张免费生图额度
  • User 已配置过腾讯云密钥并要求继续用混元

When NOT to Use:

  • User 只想免费快速出图、零配置 → 用 freeimg-z-image skill(z-image-turbo,免注册免领取)
  • User 不愿花几分钟领取免费资源包(虽然不领也不产生费用,但没有资源包时按量计费)

Core Pattern

Step 0: 首次使用 — 免费领取资源包并配置凭据

额度领取(免费,全行业开发者可领;网页版有同款图文教程卡片):

  1. 领激励资源包:微信公众平台「行业能力 → 小程序成长计划」领取资源包 (10 万张 AI 生图 + 10 亿 Token,6 个月有效),点「去使用」创建一个 云开发环境,记下环境 ID——资源包就绑定在这个环境上

  2. 建密钥:腾讯云控制台 访问管理 → API 密钥管理 「新建密钥」,复制 SecretId 与 SecretKey

  3. 写配置(只需一次,不要把密钥写进仓库、日志或对话输出):

    mkdir -p ~/.freeimg-hunyuan && printf "TCB_ENV_ID=你的环境ID\nTCB_SECRET_ID=你的SecretId\nTCB_SECRET_KEY=你的SecretKey\n" > ~/.freeimg-hunyuan/config.env && chmod 600 ~/.freeimg-hunyuan/config.env
    

脚本按以下优先级读取凭据:环境变量 TCB_ENV_ID / TCB_SECRET_ID / TCB_SECRET_KEY → 配置文件 ~/.freeimg-hunyuan/config.env。都没有时打印上述引导退出。

依赖说明:脚本用官方 @cloudbase/node-sdk(网关鉴权是自定义签名,不自行复刻), 首次运行自动装到 ~/.freeimg-hunyuan/sdk(需本机有 node + npm,十几秒),之后复用。

Step 1: 生成图片

# 文生图
scripts/generate.mjs --prompt "提示词" --out 输出.jpg [--size 1024x1024] [--no-revise] [--footnote "品牌名"]
# 垫图(图生图):--image 接图片路径、base64 或 data URL
scripts/generate.mjs --prompt "提示词" --image 垫图.jpg --out 输出.jpg
  • --size:只支持 1024x1024 / 1280x720 / 720x1280 / 2048x512 (上游限制:宽高 [512,2048] 且面积 ≤ 1024x1024)
  • --no-revise:关闭模型自动润色提示词(默认开启)
  • --footnote:右下角水印文字 ≤16 字符;默认单个空格=无水印 (去水印的合规责任在使用方)
  • 提示词上限 4000 字,中文即可
  • 429/5xx 已内置 2 秒重试一次;仍失败按错误提示处理

Step 2: 交付

  • 生成后先查看图片(Read 工具)确认质量再交给用户;不满意换提示词重生成
  • 返回的图片 URL 是签名地址会过期,脚本已立即下载落盘,只交付本地文件
  • 垫图模式提示词写「保持构图,把 ×× 换成 ××」这类改图指令效果更好

Read the full file on GitHub · 97 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 · 97 lines · 246 tokens per session scan B 68d2b503e0b1

Subscribe to this mod's changes

freeimg-hunyuan is a skill published in the GitHub repository wu529778790/shenzjd-skills (3 stars, last pushed 28d ago), licensed MIT. It adds 246 tokens to every session and 1,840 once invoked, about $0.0010 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.