Skip to content

SkyReels-V1

Generate human centred video from text or images

Visit official site

What SkyReels-V1 is

The model is described as an open source human centred video foundation model fine tuned on high quality film and television clips.

What you can do with it

  • Generate video from text or from an image
  • Capture facial expressions and natural motion combinations
  • Produce cinema grade footage from film training data

Getting started

  • Clone the repository to a local machine
  • Install dependencies from requirements.txt
  • Set resolution, frame rate and prompt parameters
  • Start inference with video_generate.py

Pros & cons

✓ What we like

  • Consumer level GPU inference with optimised memory use
  • Cinema grade lighting from high quality film data

! What to watch out for

  • Inference needs configured resolution, frame rate and prompts
  • Dependencies are installed before running the generation script

FAQ

Which generation modes are listed?

The feature list names text to video and image to video generation.

How is inference run?

The how to section names the video_generate.py script with a model ID and task type.

Last reviewed: 2026-11-15

More AI video generation tools

View all →

How we review