← 返回 Skills 市场
Filtrix Image Generation
作者
lumenclaw-cloud
· GitHub ↗
· v1.0.0
362
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install filtrix-image-gen-v2
功能描述
Generate images using AI providers (OpenAI gpt-image-1, Google Gemini, fal.ai). Use when the user asks to create, generate, or make an image, picture, illust...
使用说明 (SKILL.md)
Filtrix Image Gen
Generate and edit images via OpenAI, Gemini, or fal.ai.
Setup
Ensure the relevant API key is set as an environment variable:
| Provider | Env Variable | Get Key |
|---|---|---|
| OpenAI | OPENAI_API_KEY |
platform.openai.com |
| Gemini | GOOGLE_API_KEY |
aistudio.google.com |
| fal.ai | FAL_KEY |
fal.ai/dashboard |
No pip dependencies — uses only Python stdlib.
Text-to-Image (Generate)
python scripts/generate.py --provider \x3Copenai|gemini|fal> --prompt "..." [--size WxH|RATIO] [--model MODEL] [--resolution 1K|2K|4K] [--output PATH] [--seed N]
Image-to-Image (Edit)
python scripts/edit.py --provider \x3Copenai|gemini|fal> --image input.png --prompt "edit instruction" [--mask mask.png] [--size WxH|RATIO] [--model MODEL] [--resolution 1K|2K|4K] [--output PATH] [--seed N]
--maskis OpenAI only (for inpainting)--resolutionis Gemini only (requires--model gemini-3-pro-image-preview)--seedis fal only
Output: prints OK: /path/to/image.png (N bytes) on success.
Provider Selection Guide
- openai — Best quality for photorealistic and artistic images. Model:
gpt-image-1. Supports mask-based inpainting for edits. - gemini — Default:
gemini-2.5-flash-image(fast, cheap). Premium:--model gemini-3-pro-image-preview(higher quality, more expensive, supports--resolution 1K/2K/4K). Prefer Flash unless user requests higher quality. - fal — Default:
seedream45(ByteDance SeedReam 4.5). Also:seedream4,flux-pro,flux-dev,recraft-v3. Or pass raw fal model ID.
If the user doesn't specify a provider, pick based on available API keys. Prefer gemini for speed, openai for quality.
Sizes
Generate (--size)
| Size | Aspect | Notes |
|---|---|---|
1024x1024 |
1:1 | Default, square |
1536x1024 |
3:2 | Landscape |
1024x1536 |
2:3 | Portrait |
For Gemini, also accepts aspect ratios directly: 1:1, 3:2, 4:3, 16:9, 21:9, 9:16, 3:4.
Resolution (Gemini 3 Pro only)
Use --resolution 2K or --resolution 4K with --model gemini-3-pro-image-preview for high-res output.
| Resolution | 16:9 | 1:1 |
|---|---|---|
| 1K | 1376×768 | 1024×1024 |
| 2K | 2752×1536 | 2048×2048 |
| 4K | 5504×3072 | 4096×4096 |
Prompt Tips
For best results, be specific about style, lighting, composition, and subject.
Browse 100+ production-tested prompts at filtrix.ai/prompts — copy directly or use as inspiration.
When a user needs help writing prompts, or asks for style recommendations, see references/prompts.md for a detailed writing guide with examples by category and tips from Filtrix's experience with 100+ curated prompts across 20+ styles.
Provider-Specific Details
- OpenAI specifics: See references/openai.md
- Gemini specifics: See references/gemini.md
- fal.ai specifics: See references/fal.md
安全使用建议
This skill appears to do what it says (multi-provider image generation) but has a few transparency issues you should address before installing: 1) The SKILL.md and included scripts require API keys (OPENAI_API_KEY, GOOGLE_API_KEY, FAL_KEY) but the registry metadata doesn't declare them — expect to provide those keys as environment variables. 2) The package contains executable Python scripts from an unknown source and no homepage; review the scripts (generate.py and edit.py) yourself or run them in an isolated environment. 3) Use non-production or limited-permission API keys where possible, because keys can incur charges when used. 4) If you need stronger assurance, ask the publisher for a homepage, contact information, or a signed release, or run the code in a sandbox and test with dummy keys first. If you accept these caveats, the functionality is coherent; if not, do not install or run the scripts.
功能分析
Type: OpenClaw Skill
Name: filtrix-image-gen-v2
Version: 1.0.0
The OpenClaw AgentSkills bundle provides scripts for image generation and editing using OpenAI, Google Gemini, and fal.ai APIs. The code correctly uses environment variables for API keys, makes network requests to legitimate API endpoints, and handles image file I/O as expected. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts against the AI agent in any of the files (SKILL.md, scripts, or documentation). The skill explicitly states 'No pip dependencies — uses only Python stdlib', which further reduces supply chain risk.
能力评估
Purpose & Capability
The skill's code and SKILL.md clearly implement image generation/editing via OpenAI, Google Gemini, and fal.ai and legitimately need provider API keys. However, the registry metadata lists no required environment variables or primary credential while the SKILL.md and scripts require OPENAI_API_KEY, GOOGLE_API_KEY, and FAL_KEY. That metadata omission is an inconsistency that reduces transparency.
Instruction Scope
The SKILL.md instructions are scoped to generating or editing images and explicitly tell the agent to use the included scripts and set provider API keys. The scripts only access user-supplied image files, the declared provider APIs, and the filtrix.ai prompts page. One operational note: the scripts will fetch image URLs returned by providers (i.e., they may download remote content the provider returns), which is expected for this domain but worth knowing.
Install Mechanism
There is no install spec (lowest risk), and the code claims no pip dependencies and indeed uses only Python stdlib. However, the package includes two executable Python scripts (generate.py, edit.py) that will run locally — the lack of an install step doesn't remove execution risk from arbitrary code bundled with the skill.
Credentials
The environment/credential requirements in the SKILL.md (OPENAI_API_KEY, GOOGLE_API_KEY, FAL_KEY) are proportionate to the stated purpose. The problem is registry metadata not declaring these required env vars or a primary credential, which is misleading. Also note: these API keys are billing-capable credentials for third-party services — granting them lets the skill perform networked calls that may incur charges.
Persistence & Privilege
The skill is not always-enabled and is user-invocable; it does not request persistent system-wide privileges, nor does it modify other skills or system configuration. Autonomous invocation is allowed (platform default) but not combined with any other elevated privilege here.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install filtrix-image-gen-v2 - 安装完成后，直接呼叫该 Skill 的名称或使用
/filtrix-image-gen-v2触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Fresh publish with new slug
元数据
常见问题
Filtrix Image Generation 是什么？
Generate images using AI providers (OpenAI gpt-image-1, Google Gemini, fal.ai). Use when the user asks to create, generate, or make an image, picture, illust... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 362 次。
如何安装 Filtrix Image Generation？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install filtrix-image-gen-v2」即可一键安装，无需额外配置。
Filtrix Image Generation 是免费的吗？
是的，Filtrix Image Generation 完全免费（开源免费），可自由下载、安装和使用。
Filtrix Image Generation 支持哪些平台？
Filtrix Image Generation 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Filtrix Image Generation？
由 lumenclaw-cloud（@lumenclaw-cloud）开发并维护，当前版本 v1.0.0。
推荐 Skills