Skip to content

Wan2.1-FLF2V-14B

An open video model for 480P and 720P output

Visit official site

What wan2-1-flf2v-14b is

The model is an open-source video generation model aimed at multiple generation tasks. It runs on consumer GPUs and produces 480P and 720P video from text or images.

What you can do with it

  • Clone the model repository
  • Install listed dependencies
  • Run text-to-video generation with a prompt

Key features

  • Text-to-video and image-to-video
  • Chinese and English text support
  • Wan-VAE encoding and decoding

Pros & cons

✓ What we like

  • Runs on consumer-grade GPUs
  • Wan-VAE keeps timing information in encoding

! What to watch out for

  • Model weights are downloaded with huggingface-cli or modelscope-cli
  • Generation is run from a command with parameters and a prompt

FAQ

What tasks are listed?

Text-to-video and image-to-video.

How are weights obtained?

With huggingface-cli or modelscope-cli.

Last reviewed: 2026-11-15

More AI video generation tools

View all →

How we review