首页龙虾技能列表 › Image Generation — Image工具

🎨 Image Generation — Image工具

v1.0.0

Create AI images with GPT Image, Gemini Nano Banana 图像工具, FLUX, Imagen, and top providers using prompt engineering, style control, and smart editing.

0· 69·0 当前·0 累计
by @onlyloveher·MIT-0
下载技能包
License
MIT-0
最后更新
2026/3/27
安全扫描
VirusTotal
无害
查看报告
OpenClaw
安全
high confidence
The skill's files and runtime instructions are coherent with an image-generation helper: it requests only provider API keys optionally, stores local preferences under ~/image-generation/, and does not ask for unrelated credentials or perform hidden installs.
评估建议
This skill appears internally consistent for image-generation tasks. Before installing: - Know that prompts and any reference images you provide will be sent to the chosen third‑party provider(s). Do not submit confidential or sensitive images/text to those providers unless you trust them. - The skill will create ~/image-generation/ and may save memory.md and optional history.md — review those files and avoid logging sensitive prompt content if privacy is a concern. - Provider API keys are optio...
详细分析 ▾
用途与能力
Name/description (AI image generation, multi-provider routing, prompt engineering) match the actual artifacts: multiple provider guides, prompting patterns, and local memory usage. The optional environment variables and config path correspond to expected provider API keys and a local workspace. Minor metadata inconsistencies exist (SKILL.md/_meta.json/registry show different versions and slightly different owner IDs), which look like bookkeeping issues rather than functional deviations.
指令范围
Runtime instructions (SKILL.md and companion docs) limit actions to: resolving model aliases, choosing providers, calling provider APIs, and storing user preferences/history under ~/image-generation/. Setup checks only test for the presence of provider env vars and explicitly warns what data is sent externally. There are no instructions to read unrelated system files, exfiltrate secrets, or contact unexpected endpoints. The guidance explicitly states prompts and reference images will be sent to chosen providers (which is expected).
安装机制
This is an instruction-only skill with no install spec and no code files to execute. That minimizes on-disk execution risk. The documented API endpoints are standard provider endpoints (OpenAI, Google, Replicate, BFL, Leonardo, Ideogram, Discord for Midjourney). No downloads, executables, or obscure URLs are referenced.
凭证需求
No required env vars are declared; several provider API keys are listed as optional (OPENAI_API_KEY, GEMINI_API_KEY, BFL_API_KEY, GOOGLE_CLOUD_PROJECT, REPLICATE_API_TOKEN, LEONARDO_API_KEY, IDEOGRAM_API_KEY), which is proportional to a multi-provider image skill. The skill does require a local config path (~/image-generation/) to persist preferences/history — this is reasonable, but users should be aware that prompt text and reference images may be recorded in those files unless they opt out of logging.
持久化与权限
always: false and no install hooks are present. The skill stores only its own workspace under ~/image-generation/ (memory.md, optional history.md) and does not request system-wide config changes or other skills' credentials. It does not store API keys per its documentation. Autonomous invocation is allowed by default (normal for skills) but not combined with any other high-risk factors here.
安全有层次,运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发,无需署名。

运行时依赖

🖥️ OSLinux · macOS · Windows

版本

latestv1.0.02026/3/27

- Initial release of the AI Image Generation skill, providing modern AI image creation and editing across multiple providers. - Includes updated 2026 benchmark-guided model selection, with clear guidance on best practices and common pitfalls. - Supports prompt engineering, style control, and automated model alias resolution for consistent results. - Documents privacy practices and all external endpoints used. - Adds migration guidance, troubleshooting, and links to related skills for advanced workflows.

● 无害

安装命令 点击复制

官方npx clawhub@latest install image-generation-zhouli
镜像加速npx clawhub@latest install image-generation-zhouli --registry https://cn.clawhub-mirror.com

技能文档

Setup

On first use, read setup.md.

当...时 到 使用

User needs AI-generated visuals, edits, or consistent image sets. Use this skill to pick the right model, write stronger prompts, and avoid outdated model choices.

Architecture

User preferences persist in ~/image-generation/. See memory-template.md for setup.

~/image-generation/
├── memory.md      # Preferred providers, project context, winning recipes
└── history.md     # Optional generation log

Quick Reference

TopicFile
Initial setupsetup.md
Memory templatememory-template.md
Migration guidemigration.md
Benchmark snapshotsbenchmarks-2026.md
Prompt techniquesprompting.md
API handlingapi-patterns.md
GPT Image (OpenAI)gpt-image.md
Gemini and Imagen (Google)gemini.md
FLUX (Black Forest Labs)flux.md
Midjourneymidjourney.md
Leonardoleonardo.md
Ideogramideogram.md
Replicatereplicate.md
Stable Diffusionstable-diffusion.md

Core Rules

1. Resolve aliases 到 official 模型 IDs 第一个

Community names shift quickly. Before calling an API, map the nickname to the provider model ID.

Community labelOfficial model ID to try firstNotes
Nano Bananagemini-2.5-flash-image-previewCommon nickname, not an official Google model ID
Nano Banana 2 / ProVerify provider docsUsually a provider preset over Gemini image models
GPT Image 1.5gpt-image-1.5Current OpenAI high-tier image model
GPT Image mini / iMinigpt-image-1-miniBudget/faster OpenAI variant
FLUX 2 Pro / Maxflux-pro / flux-ultraMany platforms rename these SKUs

2. Pick models 由 task, 不 由 hype

TaskFirst choiceBackup
Exact text in imagegpt-image-1.5Ideogram
Multi-turn editsgemini-2.5-flash-image-previewflux-kontext-pro
Photoreal hero shotsimagen-4.0-ultra-generate-001flux-ultra
Fast low-cost draftsgpt-image-1-miniimagen-4.0-fast-generate-001
Character/product consistencyflux-kontext-maxgpt-image-1.5 with references
Local no-API workflowsflux-schnellSDXL

3. 使用 benchmark tables 作为 dated snapshots

Benchmarks drift weekly. Use benchmarks-2026.md as a starting point, then recheck current rankings when quality is critical.

4. Draft cheap, finish expensive

Start with 1-4 low-cost drafts, pick one, then upscale or rerender only the winner.

5. Keep fallback chain

If the preferred model is unavailable, fallback by tier: 1) same provider lower tier, 2) cross-provider equivalent, 3) local/open model.

6. Treat DALL-E 作为 legacy

OpenAI lists DALL-E 2/3 as legacy. Do not use them as default for new projects.

Common Traps

  • 使用 vendor nicknames 作为 模型 IDs -> API errors 和 wasted retries
  • Assuming "Nano Banana Pro" 或 "FLUX 2" universal IDs -> provider mismatch
  • Copying 旧的 DALL-E prompt habits -> weaker 输出 vs modern GPT/Gemini image models
  • Comparing text-到-image 和 image-editing scores 作为 如果 它们 是 相同 benchmark
  • Optimizing every draft 在 max quality -> cost spikes 没有 quality gain

Security & Privacy

Data leaves machine:

  • Prompt text
  • Reference images 当...时 editing 或 样式 matching

Data stays local:

  • Provider preferences 在...中 ~/image-generation/memory.md
  • 可选 local history file

skill 做 不:

  • Store API keys
  • 上传 files outside chosen provider requests
  • Persist generated images unless 用户 asks 到 保存 them

External Endpoints

ProviderEndpointData SentPurpose
OpenAIapi.openai.comPrompt text, optional input imagesGPT Image generation/editing
Google Gemini APIgenerativelanguage.googleapis.comPrompt text, optional input imagesGemini image generation/editing
Google Vertex AIaiplatform.googleapis.comPrompt text, optional input imagesImagen 4 generation
Black Forest Labsapi.bfl.aiPrompt text, optional input imagesFLUX generation/editing
Replicateapi.replicate.comPrompt text, optional input imagesHosted third-party image models
Midjourneydiscord.comPrompt textMidjourney generation via Discord workflows
Leonardocloud.leonardo.aiPrompt text, optional input imagesLeonardo generation/editing
Ideogramapi.ideogram.aiPrompt textTypography-focused image generation
No other data is sent externally.

Migration

If upgrading from a previous version, read migration.md before updating local memory structure.

Trust

This skill may send prompts and reference images to third-party AI providers. Only install if you trust those providers with your content.

Related Skills

Install with clawhub install if user confirms:
  • image-编辑 - Specialized inpainting, outpainting, 和 mask workflows
  • video-generation - Convert image concepts 进入 video pipelines
  • colors - Build palettes 对于 visual consistency 穿过 assets
  • ffmpeg - Post-process image sequences 和 exports

Feedback

  • 如果 useful: clawhub star image-generation
  • Stay updated: clawhub 同步
数据来源:ClawHub ↗ · 中文优化:龙虾技能库
OpenClaw 技能定制 / 插件定制 / 私有工作流定制

免费技能或插件可能存在安全风险,如需更匹配、更安全的方案,建议联系付费定制

了解定制服务