skills.rest
valentinuuiuiu
valentinuuiuiuCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

inference-sh-cli

Access over 150 AI apps for image, video, and text generation via the infsh CLI.

Updated Aug 23, 2026
Search Tags:#cli#image generation#search#inference.sh#video creation#ai-apps
One-click install
npx skills add https://github.com/valentinuuiuiu/vikarma --skill inference-sh-cli-valentinuuiuiu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: inference-sh-cli
Source: https://github.com/valentinuuiuiu/vikarma/tree/main/hermes_agent/optional-skills/devops/cli
Command: npx skills add https://github.com/valentinuuiuiu/vikarma --skill inference-sh-cli-valentinuuiuiu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the problem of manually managing and accessing multiple AI apps for various tasks like image generation, video creation, and more, through a unified terminal tool.

Core Features & Use Cases

  • Unified CLI Access: Access over 150 AI apps through the infsh CLI without managing multiple provider APIs.
  • Image and Video Generation: Create images and videos with various AI models like FLUX, Veo, and Seedance.
  • AI-Powered Search: Search for information and research using Tavily and Exa.
  • Use Case: Need to create a futuristic city image? Run the 'google/gemini-2-5-flash-image' command with a prompt and generate the image in seconds.

Quick Start

Generate an image with the Gemini AI model:

infsh app run google/gemini-2-5-flash-image --input '{"prompt": "futuristic city", "num_images": 1}' --json

Frequently Asked Questions about inference-sh-cli

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run multiple AI apps from the terminal without managing individual provider APIs?▼

You can run over 150 AI apps from the terminal without individual API management by using the unified infsh CLI. This tool provides a single access point to execute commands for various AI applications directly.

How do I generate an image via CLI using the Gemini model?▼

To generate an image via CLI, execute the `infsh app run google/gemini-2-5-flash-image` command with your prompt and desired image count in JSON format. This returns the generated image output directly to your terminal.

Can I create videos and perform AI-powered search using a single command line tool?▼

Yes, you can create videos using models like Veo and Seedance while also performing AI-powered search with Tavily and Exa. The infsh CLI consolidates these diverse AI capabilities into a single terminal interface.

What is the best way to access 150+ AI applications for image and video generation?▼

The best way to access 150+ AI applications for image and video generation is through a unified CLI tool. This approach eliminates the need to manually configure and manage multiple separate provider APIs.

Do I need to set up individual API keys for each AI model when using a unified CLI?▼

No, you do not need to manage individual API keys for each AI model. A unified CLI tool handles the backend connections allowing you to access over 150 different AI applications seamlessly through one interface.

Related Skills

Explore More Product & Management Skills→
LynxLabVNLynxLabVN

inference-sh-cli

Run AI applications from the terminal via the inference.sh CLI.

Official
Intermediate
42atom42atom

twitter-media

Extract tweet text, author, and media from Twitter/X URLs via fxTwitter API.

Community
Intermediate
ldzhhxxldzhhxx
1

inference-sh-cli

Execute over 150 AI apps via the infsh CLI terminal commands.

Community
Intermediate
nadicodeainadicodeai

inference-sh-cli

Execute 150+ AI apps in the cloud via a single CLI.

Official
Advanced