← 返回 Skills 市场
Ai Image Gen Pro
作者
bingze00000
· GitHub ↗
· v1.0.0
· MIT-0
183
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install ai-image-gen-pro
功能描述
Generate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image,...
使用说明 (SKILL.md)
\r \r
AI Image Generation\r
\r
Generate images with 50+ AI models via inference.sh CLI.\r
\r
\r
\r
Quick Start\r
\r
Requires inference.sh CLI (
infsh). Install instructions\r \r
infsh login\r
\r
# Generate an image with FLUX\r
infsh app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut in space"}'\r
```\r
\r
\r
## Available Models\r
\r
| Model | App ID | Best For |\r
|-------|--------|----------|\r
| FLUX Dev LoRA | `falai/flux-dev-lora` | High quality with custom styles |\r
| FLUX.2 Klein LoRA | `falai/flux-2-klein-lora` | Fast with LoRA support (4B/9B) |\r
| **P-Image** | `pruna/p-image` | Fast, economical, multiple aspects |\r
| **P-Image-LoRA** | `pruna/p-image-lora` | Fast with preset LoRA styles |\r
| **P-Image-Edit** | `pruna/p-image-edit` | Fast image editing |\r
| Gemini 3 Pro | `google/gemini-3-pro-image-preview` | Google's latest |\r
| Gemini 2.5 Flash | `google/gemini-2-5-flash-image` | Fast Google model |\r
| Grok Imagine | `xai/grok-imagine-image` | xAI's model, multiple aspects |\r
| Seedream 4.5 | `bytedance/seedream-4-5` | 2K-4K cinematic quality |\r
| Seedream 4.0 | `bytedance/seedream-4-0` | High quality 2K-4K |\r
| Seedream 3.0 | `bytedance/seedream-3-0-t2i` | Accurate text rendering |\r
| Reve | `falai/reve` | Natural language editing, text rendering |\r
| ImagineArt 1.5 Pro | `falai/imagine-art-1-5-pro-preview` | Ultra-high-fidelity 4K |\r
| FLUX Klein 4B | `pruna/flux-klein-4b` | Ultra-cheap ($0.0001/image) |\r
| Topaz Upscaler | `falai/topaz-image-upscaler` | Professional upscaling |\r
\r
## Browse All Image Apps\r
\r
```bash\r
infsh app list --category image\r
```\r
\r
## Examples\r
\r
### Text-to-Image with FLUX\r
\r
```bash\r
infsh app run falai/flux-dev-lora --input '{\r
"prompt": "professional product photo of a coffee mug, studio lighting"\r
}'\r
```\r
\r
### Fast Generation with FLUX Klein\r
\r
```bash\r
infsh app run falai/flux-2-klein-lora --input '{"prompt": "sunset over mountains"}'\r
```\r
\r
### Google Gemini 3 Pro\r
\r
```bash\r
infsh app run google/gemini-3-pro-image-preview --input '{\r
"prompt": "photorealistic landscape with mountains and lake"\r
}'\r
```\r
\r
### Grok Imagine\r
\r
```bash\r
infsh app run xai/grok-imagine-image --input '{\r
"prompt": "cyberpunk city at night",\r
"aspect_ratio": "16:9"\r
}'\r
```\r
\r
### Reve (with Text Rendering)\r
\r
```bash\r
infsh app run falai/reve --input '{\r
"prompt": "A poster that says HELLO WORLD in bold letters"\r
}'\r
```\r
\r
### Seedream 4.5 (4K Quality)\r
\r
```bash\r
infsh app run bytedance/seedream-4-5 --input '{\r
"prompt": "cinematic portrait of a woman, golden hour lighting"\r
}'\r
```\r
\r
### Image Upscaling\r
\r
```bash\r
infsh app run falai/topaz-image-upscaler --input '{"image_url": "https://..."}'\r
```\r
\r
### Stitch Multiple Images\r
\r
```bash\r
infsh app run infsh/stitch-images --input '{\r
"images": ["https://img1.jpg", "https://img2.jpg"],\r
"direction": "horizontal"\r
}'\r
```\r
\r
## Related Skills\r
\r
```bash\r
# Full platform skill (all 150+ apps)\r
npx skills add inference-sh/skills@infsh-cli\r
\r
# Pruna P-Image (fast & economical)\r
npx skills add inference-sh/skills@p-image\r
\r
# FLUX-specific skill\r
npx skills add inference-sh/skills@flux-image\r
\r
# Upscaling & enhancement\r
npx skills add inference-sh/skills@image-upscaling\r
\r
# Background removal\r
npx skills add inference-sh/skills@background-removal\r
\r
# Video generation\r
npx skills add inference-sh/skills@ai-video-generation\r
\r
# AI avatars from images\r
npx skills add inference-sh/skills@ai-avatar-video\r
```\r
\r
Browse all apps: `infsh app list`\r
\r
## Documentation\r
\r
- [Running Apps](https://inference.sh/docs/apps/running) - How to run apps via CLI\r
- [Image Generation Example](https://inference.sh/docs/examples/image-generation) - Complete image generation guide\r
- [Apps Overview](https://inference.sh/docs/apps/overview) - Understanding the app ecosystem\r
\r
安全使用建议
This skill is an instruction-only helper for the inference.sh CLI and appears internally consistent. Before using it: (1) verify and trust the inference.sh CLI install instructions and the installer source (the SKILL.md links to a raw GitHub URL); (2) review what happens when you run infsh login (what auth/token is created and where it is stored) and avoid reusing high-privilege credentials; (3) be aware the skill references paid models and a paid pricing entry in _meta.json; (4) note the small metadata mismatch (the metadata lists the Python 'requests' package even though there is no code) — not harmful but worth questioning the author if you need guarantees. If you need stronger assurance, ask the publisher for an explicit provenance link to the official inference.sh project and a justification for the metadata entry.
功能分析
Type: OpenClaw Skill
Name: ai-image-gen-pro
Version: 1.0.0
The skill bundle provides instructions and tool definitions for an AI agent to interact with the inference.sh CLI (infsh) for image generation. The SKILL.md file correctly restricts the agent's capabilities to the 'infsh' command and provides legitimate examples for text-to-image, editing, and upscaling tasks. No evidence of malicious intent, data exfiltration, or prompt injection was found; the use of external installation links and CLI login commands is consistent with the stated purpose of integrating a third-party AI service.
能力评估
Purpose & Capability
Name and description match the runtime instructions: the SKILL.md tells the agent to use the infsh CLI to run image-generation apps (Flux, Gemini, Grok, Seedream, Reve, etc.). Nothing requested in the files (no env vars, no config paths) is unexpected for an image-generation CLI helper.
Instruction Scope
Instructions stay within scope: examples only call infsh (infsh login, infsh app run, infsh app list). The SKILL.md does not instruct the agent to read unrelated system files, collect extra secrets, or transmit data to endpoints outside the inference.sh ecosystem. It references external docs and example commands that will cause the user/agent to authenticate to inference.sh, which is expected for this function.
Install Mechanism
There is no install spec in the registry (instruction-only), which is low risk. The SKILL.md links to a raw GitHub URL for infsh install instructions; while this is typical for CLI install docs, users should verify the origin of any installer script they run. No archives or downloads are performed by the skill itself.
Credentials
SKILL.md declares no required environment variables or credentials, which aligns with its function. Minor inconsistency: _meta.json lists a runtime requirement of the Python package 'requests' despite there being no code files that would need it — this appears to be metadata noise rather than a necessary credential or secret.
Persistence & Privilege
The skill is not always-enabled and is user-invocable. It does not request persistent agent privileges, modify other skills, or claim system-wide configuration access.
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 ai-image-gen-pro - 安装完成后,直接呼叫该 Skill 的名称或使用
/ai-image-gen-pro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
Initial release of AI Image Generation skill.
- Generate images with 50+ AI models via inference.sh CLI, including FLUX, Gemini, Grok, Seedream, and Reve.
- Supports text-to-image, image-to-image, inpainting, image editing, upscaling, LoRA, and text rendering.
- Quick start instructions and detailed CLI usage examples included.
- Comprehensive model table for selecting best models by use-case.
- Reference to related skills, documentation, and app browsing commands for further capabilities.
元数据
常见问题
Ai Image Gen Pro 是什么?
Generate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 183 次。
如何安装 Ai Image Gen Pro?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ai-image-gen-pro」即可一键安装,无需额外配置。
Ai Image Gen Pro 是免费的吗?
是的,Ai Image Gen Pro 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Ai Image Gen Pro 支持哪些平台?
Ai Image Gen Pro 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 Ai Image Gen Pro?
由 bingze00000(@bingze00000)开发并维护,当前版本 v1.0.0。
推荐 Skills