# Helios

Helios is a 14B long-video model that streams minute-scale video in real time while you change the prompt. Its authors reach real time without the usual shortcuts such as KV caches, sparse attention or quantization, and the weights are Apache-2.0.

Organization: PKU-YuanGroup. Released: March 2026. Kind: Live video.

## What you control

- A text prompt
- Prompt changes while the video streams
- An optional starting image

## License

Weights: Available (https://huggingface.co/BestWishYsh/Helios-Distilled). Declared license: Apache-2.0.
The weights' model card declares Apache-2.0, a permissive license that allows commercial use. Check what the model was built on, because a base model's terms can still apply.

## Real-time

Real-time, per authors. Minute-scale video at 19.5 fps end to end.

## How to run it

1. Clone PKU-YuanGroup/Helios, create a Python 3.11 conda environment, install PyTorch for your CUDA version, then run bash install.sh.
2. Download the checkpoint you need from Hugging Face: Helios-Base, Helios-Mid or Helios-Distilled.
3. Run the inference scripts in the repository, or load the model through Diffusers, which supports Helios.

## Where to try

- [Hugging Face Space](https://huggingface.co/spaces/BestWishYsh/Helios-14B-RealTime-AOTI): Demo Space linked from the official repository.
- [Reactor](https://www.reactor.inc/models/helios)
- [Windflow](https://windflow.online/models/helios)

## Sources

- [Project source](https://github.com/PKU-YuanGroup/Helios)
- [Weights and model card](https://huggingface.co/BestWishYsh/Helios-Distilled)
- [Project page](https://pku-yuangroup.github.io/Helios-Page)

## Questions

### Is Helios open source?

Helios publishes downloadable weights under Apache-2.0. The declared license is permissive.

### Can I use Helios commercially?

The weights' model card declares Apache-2.0, a permissive license that allows commercial use. Check what the model was built on, because a base model's terms can still apply.

### Does Helios run in real time?

Yes, according to its authors. Minute-scale video at 19.5 fps end to end. This directory has not measured it independently.

### Where can I try Helios?

You can try it on Hugging Face Space, Reactor and Windflow.

### What does Helios take as input?

You give it a text prompt, prompt changes while the video streams and an optional starting image.

### How do I run Helios?

Following the official instructions: Clone PKU-YuanGroup/Helios, create a Python 3.11 conda environment, install PyTorch for your CUDA version, then run bash install.sh. Download the checkpoint you need from Hugging Face: Helios-Base, Helios-Mid or Helios-Distilled. Run the inference scripts in the repository, or load the model through Diffusers, which supports Helios.

### What are alternatives to Helios?

Similar models in this directory include EdenLive (open weights, custom terms), Krea Realtime 14B (open weights, permissive license) and LongLive 2.0 (open weights, custom terms).

Checked 2026-10-23. Corrections: https://github.com/windflow-labs/world-model-directory