skills.rest
xu1713
xu1713COMMUNITY
Explore all skills by this author →
GitHub

inference-sh-cli

Runs 150+ cloud AI apps for image, video, audio, and search via the inference.sh CLI.

Updated Jun 5, 2026
Search Tags:#cli#image generation#video generation#inference.sh#ai apps#infsh#cloud inference
One-click install
npx skills add https://github.com/xu1713/openhorse --skill inference-sh-cli-xu1713
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: inference-sh-cli
Source: https://github.com/xu1713/openhorse/tree/main/openhorse/openhorse/optional-skills/devops/cli
Command: npx skills add https://github.com/xu1713/openhorse --skill inference-sh-cli-xu1713

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Accessing many different AI models normally requires managing separate provider APIs, credentials, and GPU infrastructure. This Skill lets you run over 150 cloud-hosted AI apps—image generation, video creation, TTS, search, 3D, and more—through a single unified CLI without any local GPU. ## Core Features & Use Cases - App Discovery: Search the inference.sh catalog with infsh app list --search to find the correct app ID before running anything. - Media Generation: Run apps like FLUX, Veo, Seedance, and Grok Imagine with JSON inputs and receive URLs to generated images and videos. - Local File Uploads: Pass local file paths (images, audio) directly in the input JSON and the CLI uploads them automatically. - Use Case: A user asks for a short drone-style video clip. You search for video apps, run google/veo-3-1-fast with a prompt, and return the generated video URL for inline display. ## Quick Start Ask the assistant to generate an image of a sunset over mountains using the inference.sh CLI, and it will search for the right app, run it, and return the image URL.

Frequently Asked Questions about inference-sh-cli

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

FAQPage Schema
How do I generate images with the inference.sh CLI?▼

First search for an image app with `infsh app list --search image`, then run it with a JSON input, for example `infsh app run falai/flux-dev-lora --input '{"prompt": "sunset over mountains"}' --json`. The JSON output contains URLs to the generated images.

How do I find the right app ID on inference.sh?▼

Never guess app IDs since they change frequently. Use `infsh app list --search <term>` or `infsh app search <query>` to find current app IDs, and `infsh app get <app-id>` to inspect an app's input schema before running it.

Can I use local files as input for inference.sh apps?▼

Yes, the CLI automatically uploads local files when you provide a path instead of a URL. Absolute paths, relative paths like ./image.png, and home directory paths like ~/Pictures/photo.jpg are all supported in any field that accepts a URL.

Why does infsh fail with authentication errors?▼

Authentication errors mean the CLI is not logged in or the API key is invalid. Run `infsh login` to authenticate via browser, verify with `infsh me`, or set the INFSH_API_KEY environment variable for CI/CD environments.

How long does video generation take with infsh?▼

Video generation apps like Veo or Seedance typically take 30-120 seconds to complete. For very long tasks, use `infsh app run <app> --input <file> --no-wait` to submit in the background and check status later with `infsh task get <task-id>`.

Related Skills

Explore More Design & Creative Skills→
NEXUZ-SYSNEXUZ-SYS

image-fetcher

Acquire web images, Playwright screenshots, and user files into a reference folder.

Official
Intermediate
teodorboevteodorboev

visual

Generate and process visual assets for social media platforms.

Community
Advanced
BalajitechlabsBalajitechlabs

photo-editor

Resize, crop, filter, and optimize images using Pillow and OpenCV.

Community
Advanced
heyu-aiheyu-ai

verify-gemini-models

Verify Gemini model availability and functionality via REST and WebSocket calls.

Official
Advanced