← Back to Skills Marketplace
mapleslove

Grs Image

by mapleslove · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
129
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install grs-image
Description
GrsAI Nano Banana Pro 图片生成工具。使用 GrsAI API 生成图片，支持中文描述。适用于室内设计效果图、开工大吉海报、设计素材生成等场景。
README (SKILL.md)

GrsAI Image Generator

GrsAI Nano Banana Pro 图片生成工具。

前提条件

pip install requests
export GRSAAI_API_KEY='your-api-key'

API 信息

模型选择

模型 支持分辨率
nano-banana-pro 1K / 2K / 4K
nano-banana-pro-vt 1K / 2K / 4K
nano-banana-pro-cl 1K / 2K / 4K
nano-banana-pro-vip 1K / 2K
nano-banana-pro-4k-vip 4K
nano-banana-fast 1K
nano-banana 1K
nano-banana-2 1K / 2K / 4K
nano-banana-2-cl 1K / 2K
nano-banana-2-4k-cl 4K

使用方式

基本用法

python skills/grs-image/scripts/grs_image.py "一只可爱的橘猫在草地上玩耍"

指定输出文件

python skills/grs-image/scripts/grs_image.py "现代简约客厅效果图" -o living_room.png

指定宽高比

# 1:1 方图
python skills/grs-image/scripts/grs_image.py "开工大吉海报" -r 1:1 -o kaigong.png

# 16:9 横图
python skills/grs-image/scripts/grs_image.py "客厅效果图" -r 16:9 -o living.png

# 9:16 竖图
python skills/grs-image/scripts/grs_image.py "阳台设计" -r 9:16 -o balcony.png

支持的宽高比：auto / 1:1 / 16:9 / 9:16 / 4:3 / 3:4 / 3:2 / 2:3 / 5:4 / 4:5 / 21:9 额外比例（nano-banana-2系列）：1:4 / 4:1 / 1:8 / 8:1

指定分辨率

# 生成2K分辨率图片（默认1K）
python skills/grs-image/scripts/grs_image.py "高清效果图" -s 2K -o hd_design.png

# 生成4K分辨率图片
python skills/grs-image/scripts/grs_image.py "超高清晰度效果图" -s 4K -o 4k_design.png

图生图（参考图）

python skills/grs-image/scripts/grs_image.py "把这张图改成奶油风" \
  -u "https://example.com/reference.png" \
  -r 16:9 -o output.png

使用快速模型

python skills/grs-image/scripts/grs_image.py "快速草图" -m nano-banana-fast

常用场景示例

室内设计效果图

python skills/grs-image/scripts/grs_image.py "现代简约风格客厅效果图，浅色地板，白墙，大窗户" -r 16:9 -s 2K -o design.png

开工大吉海报

python skills/grs-image/scripts/grs_image.py "开工大吉红金配色中国传统风格设计师专属" -r 1:1 -s 2K -o kaigong.png

设计素材

python skills/grs-image/scripts/grs_image.py "大理石纹理瓷砖样品高清图片" -r 1:1 -s 2K -o tile.png

输出示例

正在生成图片...
Prompt: 一只可爱的橘猫在草地上玩耍
Ratio: 16:9
Size: 2K
任务ID: 3-9b0ef381-a39c-4a03-8667-298380fe1fc1
生成中... 100%
图片URL: https://file1.aitohumanize.com/file/xxx.png
已保存: output.png

完成: output.png

注意事项

  • 图片生成需要 30-60 秒，分辨率越高时间越长
  • 建议先测试小图，效果满意后再生成正式图
  • 中文描述效果较好，英文也可以
  • 图片 URL 有效期 2 小时
  • 图生图的参考图支持 URL 或 Base64
Usage Guidance
This skill is largely what it says — a small Python client for a GrsAI image API — but there are two things to check before installing: (1) the registry metadata omits the required GRSAAI_API_KEY even though SKILL.md and the script require and will send it to the hard-coded endpoint (https://grsai.dakka.com.cn). Only provide a key if you trust that host and the skill owner. (2) The script hard-codes a domestic BASE_URL while documentation lists an overseas endpoint; confirm which endpoint you intend to use and consider editing the script if needed. Inspect the script source (it’s included) and, if possible, test with a low-privilege or revocable API key first. Also be aware the script will download the final image from whatever URL the API returns — verify returned URLs before trusting them if you have strict network policies. If the author or homepage is unknown, prefer caution.
Capability Analysis
Type: OpenClaw Skill Name: grs-image Version: 1.0.0 The skill bundle provides a legitimate tool for generating images using the GrsAI API. The core logic in `scripts/grs_image.py` implements standard API interaction, including task submission, status polling, and downloading the resulting image to a local file. No evidence of data exfiltration, unauthorized command execution, or malicious prompt injection was found; the code and documentation (`SKILL.md`, `references/prompts.json`) are entirely consistent with the stated purpose of image generation.
Capability Assessment
⚠ Purpose & Capability
The skill's name/description claim it calls the GrsAI API to generate images, and the included script indeed makes HTTP calls to an external GrsAI endpoint — that is coherent. However, the registry metadata lists no required environment variables or primary credential, while both SKILL.md and scripts require GRSAAI_API_KEY. This mismatch between declared requirements and actual runtime needs is unexpected.
ℹ Instruction Scope
SKILL.md provides concrete CLI usage and asks the user to set GRSAAI_API_KEY and pip-install requests. The runtime instructions and script perform only network calls to the GrsAI endpoints and write the downloaded image file to disk — all within the stated image-generation scope. The SKILL.md references both domestic and overseas API hosts, but the script hard-codes the domestic BASE_URL, which is a minor inconsistency to be aware of.
✓ Install Mechanism
There is no install spec; the skill is instruction-only with a small Python script. SKILL.md asks to pip install requests — a minimal, expected dependency. No downloads from untrusted URLs or extraction steps are present.
⚠ Credentials
The script reads GRSAAI_API_KEY from the environment and uses it as a Bearer token to an external service. The registry metadata did not declare this required credential or a primaryEnv, which is disproportionate (and potentially confusing) — users may not realize an API key will be transmitted to the hard-coded endpoint. No other unrelated credentials are requested.
✓ Persistence & Privilege
The skill does not request always:true, does not modify system or other skills' configs, and only writes an output image file. It does perform network I/O to external endpoints (expected for its purpose) but does not request elevated persistent privileges.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install grs-image
  3. After installation, invoke the skill by name or use /grs-image
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
GrsAI Nano Banana Pro 图片生成工具首发上线： - 支持通过 GrsAI API 生成图片，可用中文描述，适配多种设计场景。 - 覆盖室内设计效果图、开工大吉海报、设计素材等应用。 - 支持多模型、多分辨率（1K/2K/4K）及多宽高比选择。 - 提供图生图功能及参考图指定。 - 命令行工具形式，附使用示例与常用场景脚本。
Metadata
Slug grs-image
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Grs Image?

GrsAI Nano Banana Pro 图片生成工具。使用 GrsAI API 生成图片，支持中文描述。适用于室内设计效果图、开工大吉海报、设计素材生成等场景。 It is an AI Agent Skill for Claude Code / OpenClaw, with 129 downloads so far.

How do I install Grs Image?

Run "/install grs-image" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Grs Image free?

Yes, Grs Image is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Grs Image support?

Grs Image is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Grs Image?

It is built and maintained by mapleslove (@mapleslove); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments