wan-flf-video

Community

Create videos from start to end frames.

Authorartokun
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill enables the creation of smooth video transitions between a starting image and an ending image, leveraging advanced AI models for high-quality video generation.

Core Features & Use Cases

  • First-Last-Frame (FLF) Video Generation: Generates video sequences by interpolating between two provided keyframes.
  • Dual Hi-Lo Architecture: Utilizes a critical two-pass KSamplerAdvanced setup with separate HighNoise and LowNoise models for optimal quality.
  • Model Flexibility: Supports various UNET and Text Encoder models, including Remix NSFW, GGUF, and official fp8 variants.
  • Morphing Capabilities: Can incorporate Morph LoRAs for seamless shape transformations between frames.
  • Use Case: Transform a portrait of a person into a different person, or a landscape scene into another, with a natural, flowing transition.

Quick Start

Use the wan-flf-video skill to generate a video transitioning from 'start_image.png' to 'end_image.png' with a positive prompt describing the transformation.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 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: wan-flf-video
Download link: https://github.com/artokun/comfyui-mcp/archive/main.zip#wan-flf-video

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.