ai-image-generation

作者: skills-101

通过inference.sh CLI使用GPT-Image-2、FLUX、Gemini、Grok、Seedream、Reve及50多个模型生成AI图像。模型:GPT-Image-2、FLUX Dev LoRA、FLUX.2 Klein LoRA、Gemini 3 Pro Image、Grok Imagine、Seedream 4.5、Reve、ImagineArt。功能:文生图、图生图、图像修复、LoRA、图像编辑、超分辨率、文字渲染。用途:AI艺术、产品样机、概念艺术、社交媒体图形、营销视觉、插画。触发词:flux、图像生成、ai image、text to...

npx skills add https://github.com/skills-101/superpowers --skill ai-image-generation

Install the belt CLI skill: npx skills add belt-sh/cli

AI Image Generation

Generate images with 50+ AI models via inference.sh CLI.

AI Image Generation

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Generate an image with FLUX
belt app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut in space"}'

Available Models

ModelApp IDBest For
GPT-Image-2openai/gpt-image-2Text-to-image, editing, inpainting
FLUX Dev LoRAfalai/flux-dev-loraHigh quality with custom styles
FLUX.2 Klein LoRAfalai/flux-2-klein-loraFast with LoRA support (4B/9B)
P-Imagepruna/p-imageFast, economical, multiple aspects
P-Image-LoRApruna/p-image-loraFast with preset LoRA styles
P-Image-Editpruna/p-image-editFast image editing
Gemini 3 Progoogle/gemini-3-pro-image-previewGoogle's latest
Gemini 2.5 Flashgoogle/gemini-2-5-flash-imageFast Google model
Grok Imaginexai/grok-imagine-imagexAI's model, multiple aspects
Seedream 4.5bytedance/seedream-4-52K-4K cinematic quality
Seedream 4.0bytedance/seedream-4-0High quality 2K-4K
Seedream 3.0bytedance/seedream-3-0-t2iAccurate text rendering
Revefalai/reveNatural language editing, text rendering
ImagineArt 1.5 Profalai/imagine-art-1-5-pro-previewUltra-high-fidelity 4K
FLUX Klein 4Bpruna/flux-klein-4bUltra-cheap ($0.0001/image)
Topaz Upscalerfalai/topaz-image-upscalerProfessional upscaling

Browse All Image Apps

belt app list --category image

Examples

GPT-Image-2

belt app run openai/gpt-image-2 --input '{
  "prompt": "professional product photo of sneakers, studio lighting",
  "quality": "high"
}'

GPT-Image-2 Editing

belt app run openai/gpt-image-2 --input '{
  "prompt": "change the background to a beach at sunset",
  "images": ["https://your-image.jpg"]
}'

Text-to-Image with FLUX

belt app run falai/flux-dev-lora --input '{
  "prompt": "professional product photo of a coffee mug, studio lighting"
}'

Fast Generation with FLUX Klein

belt app run falai/flux-2-klein-lora --input '{"prompt": "sunset over mountains"}'

Google Gemini 3 Pro

belt app run google/gemini-3-pro-image-preview --input '{
  "prompt": "photorealistic landscape with mountains and lake"
}'

Grok Imagine

belt app run xai/grok-imagine-image --input '{
  "prompt": "cyberpunk city at night",
  "aspect_ratio": "16:9"
}'

Reve (with Text Rendering)

belt app run falai/reve --input '{
  "prompt": "A poster that says HELLO WORLD in bold letters"
}'

Seedream 4.5 (4K Quality)

belt app run bytedance/seedream-4-5 --input '{
  "prompt": "cinematic portrait of a woman, golden hour lighting"
}'

Image Upscaling

belt app run falai/topaz-image-upscaler --input '{"image_url": "https://..."}'

Stitch Multiple Images

belt app run infsh/stitch-images --input '{
  "images": ["https://img1.jpg", "https://img2.jpg"],
  "direction": "horizontal"
}'

Related Skills

# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli

# Pruna P-Image (fast & economical)
npx skills add inference-sh/skills@p-image

# GPT-Image-2 (OpenAI)
npx skills add inference-sh/skills@gpt-image

# FLUX-specific skill
npx skills add inference-sh/skills@flux-image

# Upscaling & enhancement
npx skills add inference-sh/skills@image-upscaling

# Background removal
npx skills add inference-sh/skills@background-removal

# Video generation
npx skills add inference-sh/skills@ai-video-generation

# AI avatars from images
npx skills add inference-sh/skills@ai-avatar-video

Browse all apps: belt app list

Documentation

来自 skills-101 的更多技能

agent-browser
skills-101
通过 inference.sh 为AI代理提供浏览器自动化。导航网页,使用@e引用与元素交互,截取屏幕截图,录制视频。功能:网页抓取、表单填写、点击、输入、拖放、文件上传、JavaScript执行。用于:网页自动化、数据提取、测试、代理浏览、研究。触发词:浏览器、网页自动化、抓取、导航、点击、填写表单、截图、浏览网页、playwright、无头浏览器、网络代理、上网、录制视频
agent-tools
skills-101
通过inference.sh CLI运行AI应用——图像生成、视频创作、LLM、搜索、3D、Twitter自动化。模型:FLUX、Veo、Gemini、Grok、Claude、Seedance、OmniHuman、Tavily、Exa、OpenRouter等。适用于运行AI应用、生成图像/视频、调用LLM、网络搜索或自动化Twitter。触发词:inference.sh、infsh、ai model、run ai、serverless ai、ai api、flux、veo、claude api、image generation、video generation、openrouter、tavily、exa search、twitter api、grok
ai-avatar-video
skills-101
通过inference.sh CLI创建AI头像和人物说话视频。推荐:P-Video-Avatar(最快、最便宜、内置TTS)。其他可选:OmniHuman、Fabric、PixVerse。音频:Inworld TTS-2(支持100多种语言、角色情感控制)、ElevenLabs、Kokoro。功能:音频驱动头像、文本转头像、唇形同步视频、人物说话生成、虚拟主持人、UGC内容。用途:AI主持人、解说视频、虚拟网红、配音、营销视频、UGC广告、游戏头像等。
ai-video-generation
skills-101
使用Google Veo、Seedance 2.0、HappyHorse、Wan、Grok等40余种模型,通过inference.sh CLI生成AI视频。模型包括:Veo 3.1、Veo 3、Seedance 2.0、HappyHorse 1.0、Wan 2.5、Grok Imagine Video、OmniHuman、Fabric、HunyuanVideo。功能:文生视频、图生视频、参考生视频、视频编辑、口型同步、虚拟人动画、视频增强、拟音音效。适用场景:社交媒体视频、营销内容、解说视频、产品演示、AI虚拟人。触发词:视频生成、AI视频、...
app-store-screenshots
skills-101
App Store和Google Play截图制作,符合精确的平台规格。涵盖iOS/Android尺寸、图库排序、设备样机和预览视频。适用于:应用商店优化、ASO、应用截图、应用预览、Play商店列表。触发词:应用商店截图、aso、应用商店优化、Play商店截图、应用预览、应用列表、iOS截图、Android截图、应用商店图片、应用样机、设备样机、应用图库、商店列表
character-design-sheet
skills-101
在AI生成图像中,通过参考表和LoRA技术保持角色一致性。涵盖转面视图、表情表、配色方案和风格一致性技巧。适用于:角色设计、游戏美术、插图、动画、漫画、视觉小说。触发词:角色设计、角色表、角色一致性、角色参考、转面视图、表情表、角色美术、角色一致性、角色概念、参考表、角色创建、原创角色设计,...
competitor-teardown
skills-101
结构化竞争分析,包含功能矩阵、SWOT、定位图和UX审查。涵盖研究框架、定价对比、评论挖掘和视觉交付物。适用于:市场研究、竞争情报、投资者演示、产品策略、销售赋能。触发词:competitor analysis、competitive analysis、competitor teardown、market research、competitive intelligence、swot analysis、competitor comparison、market landscape、competitor review、competitive...
image-to-video
skills-101
静图转视频转换指南:模型选择、运动提示和镜头移动。涵盖 Wan 2.5 i2v、Seedance、Fabric、Grok Video 及各模型的适用时机。用途:图像动画化、从静图创建视频、添加运动、产品动画。触发词:image to video、i2v、animate image、still to video、add motion to image、image animation、photo to video、animate still、wan i2v、image2video、bring image to life、animate photo、motion from image