跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

AI Image Generation

技能 已验证 活跃

Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image

目的

Generate a wide variety of AI images for artistic, professional, or marketing purposes using a diverse set of advanced AI models through a single, convenient CLI interface.

功能

  • Generate images with 50+ AI models
  • Supports text-to-image, image-to-image, inpainting, LoRA, and editing
  • Offers upscaling and text rendering capabilities
  • Integrates with the inference.sh CLI (`belt`)

使用场景

  • Creating AI art and illustrations
  • Generating product mockups and concept art
  • Producing social media graphics and marketing visuals
  • Experimenting with different AI image generation models

非目标

  • Directly embedding or managing AI models
  • Providing a graphical user interface for image generation
  • Replacing the inference.sh CLI itself

工作流

  1. Login to the inference.sh CLI (`belt login`).
  2. Select an AI model and specify generation parameters (e.g., prompt, aspect ratio).
  3. Execute the image generation command using `belt app run`.
  4. Review the generated image output.

先决条件

  • inference.sh CLI (`belt`) installed and logged in

Documentation

  • info:Configuration & parameter referenceWhile the documentation lists models and examples, specific CLI parameters beyond the basic input structure are not explicitly documented with defaults, requiring users to refer to external inference.sh documentation.

Execution

  • info:ValidationInput validation is handled by the `belt` CLI and the underlying inference.sh service, which is not explicitly detailed within the skill's markdown.

Code Execution

  • info:Error HandlingError handling is primarily managed by the `belt` CLI and the inference.sh service. The skill's markdown does not detail specific error reporting or recovery steps.

Errors

  • info:Actionable error messagesError messages would primarily come from the `belt` CLI or the inference.sh service. While the skill itself doesn't detail specific error paths, the underlying CLI is expected to provide them.

Practical Utility

  • info:Edge casesWhile the skill lists many models and capabilities, specific edge cases, failure modes, or limitations of the inference.sh CLI within this skill's context are not explicitly documented.

安装

npx skills add inferen-sh/skills

通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。

质量评分

已验证
97 /100
1 day ago 分析

信任信号

最近提交1 day ago
GitHub 所有者 inferen-sh (opens in new tab)
星标433
许可证MIT
状态
查看源代码

类似扩展

Openclaw

100

使用多提供商路由从文本生成图像和视频 — 支持 GPT Image 2.0（近乎完美的文本渲染）、Nanobanana 2、Seedream 5.0、Midjourney V8.1（统一的逼真+动漫风格）、Flux 2 Klein（经济高效的草稿）、Seedance 2.0 / Happyhorse 1.0 / Veo 3.1 视频，以及本地 ComfyUI 工作流。包含 1,446 个精选提示和风格感知提示增强。当用户想要创建图像/视频、设计素材、制作照片动画、增强提示或管理 AI 艺术工作流时使用。不适用于：通用聊天、代码生成、文档编写、现有素材的视频编辑、音频/TTS，或任何与 AI 图像/视频创建无关的任务。

技能
jau123

Qwen Image 2 Pro

99

Generate images with Alibaba Qwen-Image-2.0-Pro via inference.sh CLI. Professional text rendering, fine-grained realism, enhanced semantic adherence. Ideal for posters, banners, and text-heavy designs. Triggers: qwen image pro, qwen-image-pro, qwen 2 pro, alibaba image pro, dashscope pro, professional text rendering

技能
inferen-sh

Image Upscaling

95

Upscale and enhance images with Real-ESRGAN, Thera, Topaz, FLUX Upscaler via inference.sh CLI. Models: Real-ESRGAN, Thera (any size), FLUX Dev Upscaler, Topaz Image Upscaler. Use for: enhance low-res images, upscale AI art, restore old photos, increase resolution. Triggers: upscale image, image upscaler, enhance image, increase resolution, real esrgan, ai upscale, super resolution, image enhancement, upscaling, enlarge image, higher resolution, 4k upscale, hd upscale

技能
inferen-sh

Trader Regime

100

Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy

技能
ruvnet

Setup

100

Use first for install/update routing — sends setup, doctor, or MCP requests to the correct OMC setup flow

技能
Yeachan-Heo

Project Session Manager

100

Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions

技能
Yeachan-Heo