Ai Video Generation

Generate AI videos with Google Veo, Seedance, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 1.5 Pro, Wan 2.5, Grok Imagine...

Security Scan

The skill's instructions align with its stated purpose (installing and using the inference.sh CLI to run video models), but it directs users to run a remote install script (curl | sh) and relies on an external CLI that will accept/transfer media and requires login credentials that aren't declared — these are coherent for the task but moderately risky and worth caution.

Purpose & Capability

The name/description and the SKILL.md are consistent: the skill is an instruction-only wrapper telling the agent to use the inference.sh CLI to run many text/image->video models. All required actions (install CLI, run infsh app run ...) fit the described capability.

Instruction Scope

The runtime instructions are narrowly scoped to installing the inference.sh CLI and running its apps. They do include examples that upload media via URLs and call many third-party model apps. The instructions do not ask the agent to read unrelated system files, but they do instruct interactive 'infsh login' and to install a remote binary, which implies creation/storage of credentials and uploading user media to remote services — expected for this use case but a privacy/data-exfiltration consideration.

Install Mechanism

There is no formal install spec in metadata, but SKILL.md instructs running a remote install script via 'curl -fsSL https://cli.inference.sh | sh' which downloads binaries from dist.inference.sh. While the doc claims SHA-256 checksums are available, piping a remote script to sh and pulling binaries from a project-hosted domain is higher risk than using a vetted package repository. This is coherent with the skill's purpose but increases attack surface and trust requirements.

Credentials

The skill metadata declares no required env vars or primary credential, yet the instructions call 'infsh login' (implying an account and credentials will be created/stored). That mismatch isn't necessarily malicious, but users should expect the CLI to request authentication and persist tokens locally; those credentials are not declared in the skill manifest.

Persistence & Privilege

The skill does not request always: true, has no install spec that modifies other skills or system-wide settings, and is user-invocable. It does not demand persistent elevated privileges in the manifest.

What to consider before installing

This skill is coherent for generating videos but requires installing and trusting a third-party CLI downloaded at runtime. Before installing or running it: 1) Verify the project domain (cli.inference.sh / dist.inference.sh) and inspect the install script and published checksums yourself rather than piping blindly to sh. 2) Understand that 'infsh login' will create/stored credentials and that the CLI will send media (images/audio/video) to remote models — do not upload sensitive or private content. 3) Prefer running the installer in a sandbox or VM if you want to limit risk. 4) Check the service's privacy/terms and confirm model provenance/licensing for commercial use. 5) If you want tighter control, ask for a manifest that declares the auth token behavior and a verified install mechanism (e.g., package repository or reproducible release URL and checksum).

Generate videos with 40+ AI models via inference.sh CLI.

Quick Start

# Install CLI
curl -fsSL https://cli.inference.sh | sh && infsh login

# Generate a video with Veo
infsh app run google/veo-3-1-fast --input '{"prompt": "drone shot flying over a forest"}'

Install note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.

Available Models

Text-to-Video

Model	App ID	Best For
Veo 3.1 Fast	google/veo-3-1-fast	Fast, with optional audio
Veo 3.1	google/veo-3-1	Best quality, frame interpolation
Veo 3	google/veo-3	High quality with audio
Veo 3 Fast	google/veo-3-fast	Fast with audio
Veo 2	google/veo-2	Realistic videos
Grok Video	xai/grok-imagine-video	xAI, configurable duration
Seedance 1.5 Pro	bytedance/seedance-1-5-pro	With first-frame control
Seedance 1.0 Pro	bytedance/seedance-1-0-pro	Up to 1080p

Image-to-Video

Model	App ID	Best For
Wan 2.5	falai/wan-2-5	Animate any image
Wan 2.5 I2V	falai/wan-2-5-i2v	High quality i2v
Seedance Lite	bytedance/seedance-1-0-lite	Lightweight 720p

Avatar / Lipsync

Model	App ID	Best For
OmniHuman 1.5	bytedance/omnihuman-1-5	Multi-character
OmniHuman 1.0	bytedance/omnihuman-1-0	Single character
Fabric 1.0	falai/fabric-1-0	Image talks with lipsync
PixVerse Lipsync	falai/pixverse-lipsync	Realistic lipsync

Utilities

Tool	App ID	Description
HunyuanVideo Foley	infsh/hunyuanvideo-foley	Add sound effects to video
Topaz Upscaler	falai/topaz-video-upscaler	Upscale video quality
Media Merger	infsh/media-merger	Merge videos with transitions

Browse All Video Apps

infsh app list --category video

Examples

Text-to-Video with Veo

infsh app run google/veo-3-1-fast --input '{
  "prompt": "A timelapse of a flower blooming in a garden"
}'

Grok Video

infsh app run xai/grok-imagine-video --input '{
  "prompt": "Waves crashing on a beach at sunset",
  "duration": 5
}'

Image-to-Video with Wan 2.5

infsh app run falai/wan-2-5 --input '{
  "image_url": "https://your-image.jpg"
}'

AI Avatar / Talking Head

infsh app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "https://speech.mp3"
}'

Fabric Lipsync

infsh app run falai/fabric-1-0 --input '{
  "image_url": "https://face.jpg",
  "audio_url": "https://audio.mp3"
}'

PixVerse Lipsync

infsh app run falai/pixverse-lipsync --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "https://speech.mp3"
}'

Video Upscaling

infsh app run falai/topaz-video-upscaler --input '{"video_url": "https://..."}'

Add Sound Effects (Foley)

infsh app run infsh/hunyuanvideo-foley --input '{
  "video_url": "https://silent-video.mp4",
  "prompt": "footsteps on gravel, birds chirping"
}'

Merge Videos

infsh app run infsh/media-merger --input '{
  "videos": ["https://clip1.mp4", "https://clip2.mp4"],
  "transition": "fade"
}'

Related Skills

# Full platform skill (all 150+ apps)
npx skills add inference-sh/skills@inference-sh

# Google Veo specific
npx skills add inference-sh/skills@google-veo

# AI avatars & lipsync
npx skills add inference-sh/skills@ai-avatar-video

# Text-to-speech (for video narration)
npx skills add inference-sh/skills@text-to-speech

# Image generation (for image-to-video)
npx skills add inference-sh/skills@ai-image-generation

# Twitter (post videos)
npx skills add inference-sh/skills@twitter-automation

Browse all apps: infsh app list

Documentation

• Running Apps - How to run apps via CLI
• Streaming Results - Real-time progress updates
• Content Pipeline Example - Building media workflows