MiniMax image-01 · AI Text-to-Image Tool

MiniMax image-01 文生图工具。支持中文指令（画一张、生成图片、帮我画）和英文指令（generate an image、draw）。双端支持（中国区/国际区）。Token Plan 每日免费额度：Plus 50张/天、Max 120张/天、Ultra 800张/天。模型：image-01，输出 PNG。

Security Scan

The skill's code, instructions, and requested environment access align with a text-to-image tool that calls MiniMax's image-01 API and save results locally.

Purpose & Capability

Name/description claim text-to-image using MiniMax image-01. The script and docs only require a MINIMAX_API_KEY and call MiniMax endpoints (api.minimax.chat / api.minimax.io). Requested capabilities match the stated purpose.

Instruction Scope

SKILL.md instructs installing requests, setting MINIMAX_API_KEY, choosing region, and running the included Python script. The runtime instructions only reference the MiniMax API, local output directory, and the declared env var. The agent is not instructed to read unrelated files or system configuration.

Install Mechanism

No install spec in registry; SKILL.md suggests 'pip install requests' which is proportionate and low risk. There are no downloads from arbitrary URLs or archive extraction steps.

Credentials

Only MINIMAX_API_KEY is required (declared in SKILL.md and allowList). That single credential is appropriate for calling the external MiniMax API. No unrelated secrets, config paths, or excessive env vars are requested.

Persistence & Privilege

The skill does not request permanent/always-on installation. It does not modify other skills or system-wide settings. Autonomous invocation is allowed by default but is normal for skills and not combined with other red flags.

Assessment

This skill appears to do exactly what it claims: send your prompt to MiniMax's image-01 endpoints and save returned images locally. Before installing: ensure you trust the MiniMax endpoints you use (api.minimax.chat for China, api.minimax.io for global), keep your MINIMAX_API_KEY secret, and only provide a key from your MiniMax account. The script uses the requests library and saves base64-decoded PNG files to the output directory; you may review scripts/image_gen.py yourself if you want to confirm behavior. Network access is required for the API calls; there are no other external endpoints or unexpected credential requests.

---

MiniMax image-01 文生图工具

MiniMax image-01 文本生成图像工具。使用 MiniMax 的 image-01 模型从文字描述生成图片。

---

安装依赖

pip install requests

---

环境变量

# macOS / Linux
export MINIMAX_API_KEY=your_key

# Windows (PowerShell)
$env:MINIMAX_API_KEY="your_key"

获取 API Key：

• 中国区：https://platform.minimaxi.com/user-center/basic-information/interface-key
• 国际区：https://www.minimax.io/platform/user-center/basic-information/interface-key

---

区域选择

区域	API 地址	适用用户
中国区	https://api.minimax.chat/v1/image_generation	中国用户 / MiniMax 中国站
国际区	https://api.minimax.io/v1/image_generation	海外用户

---

快速使用

# 中国用户
python scripts/image_gen.py "你的图片描述" --region cn

# 国际用户
python scripts/image_gen.py "your prompt" --region global

---

参数说明

参数	说明	默认值
prompt	图片描述（必填）	—
--region	区域：cn 或 global（必填）	—
--aspect	比例：16:9、1:1、4:3、9:16、21:9	16:9
--n	生成数量（1-9）	1
--no-enhance	关闭 Prompt 增强	开启
--output	输出目录	当前目录

---

比例参考

比例	最佳用途
16:9	横版 / 视频封面
1:1	社交媒体 / 卡片
9:16	手机竖版 / Stories
4:3	博客 / 文档

---

Prompt 增强（默认开启）

对于短描述（<8词），自动补充专业摄影/艺术参数：

• 光影：soft natural lighting、cinematic lighting、volumetric light
• 画质：4K、sharp focus、highly detailed
• 风格：photorealistic、detailed linework、professional quality

示例：

• "一只猫" → 自动补充 soft lighting、sharp focus、4K
• "赛博朋克城市" → 自动补充 neon lighting、Blade Runner atmosphere、cinematic

关闭增强：python image_gen.py "简单描述" --region cn --no-enhance

---

输出

图片保存为 minimax_gen_1.png、minimax_gen_2.png 等。

---

每日额度（Token Plan）

套餐	每日图片额度
Starter	0（不包含图像生成）
Plus	50 张/天
Max	120 张/天
Ultra	800 张/天

额度每日零点重置，直接消耗 Token Plan 套餐额度，无需额外付费。

---

作者： Mzusama 模型： MiniMax image-01