Skills
.Work. You
Rest

vllm-omni-video-gen

Community

Generate videos with Wan2.2 and more.

Design & Creative#video#generation#diffusion#ti2v#wan2.2#omni
Authorhsliuustc0106
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Create high-quality videos from text prompts or reference images using vLLM-Omni, leveraging Wan2.2 diffusion models to simplify video generation workflows.

Core Features & Use Cases

  • Multi-mode video generation: Text-to-video (T2V), image-to-video (I2V), and text+image-to-video (TI2V) using Wan2.2 diffusion models.
  • Model flexibility: Choose from Wan2.2-T2V-A14B, Wan2.2-I2V-A14B, Wan2.2-TI2V-5B, and NextStep-1.1 with VRAM guidance.
  • Configurable parameters: adjust num_inference_steps, guidance_scale, seed, fps, and num_frames to control quality and performance.
  • Reference materials: See references/wan-models.md for detailed model specs and setup.

Quick Start

Provide a text prompt and optional reference image to Omni to generate a video using Wan2.2 models.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: vllm-omni-video-gen
Download link: https://github.com/hsliuustc0106/vllm-omni-skills/archive/main.zip#vllm-omni-video-gen

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.