Video Runtime
Developer-onlyFrame-StreamingOfficial source

Helios

Run a released 14B long-video model with training code, inference tools and distilled checkpoints.

Access and release status are source-checked descriptions, not a live uptime check. A reachable website does not establish that video playback or interaction currently works.

Open Documentation ↗View GitHub ↗

No rights-cleared product preview yet. See the official page for its latest interface.

Published by Video Runtime · Source check 2026-09-14 · Evidence method · Suggest a correction

EDITORIALLY VERIFIED PRODUCT INFORMATION

About Helios

Run a released 14B long-video model with training code, inference tools and distilled checkpoints. Compresses historical and noisy context while reducing sampling steps to produce long videos progressively.

Key features

Publishes model variants, training code, inference scripts and a Diffusers integration for long-form generation experiments.

Getting started

Open the official repository, read its current README and licence, then follow the documented environment, checkpoint and inference steps. Start with the supplied example before using your own media or data.

Real-time interaction

Compresses historical and noisy context while reducing sampling steps to produce long videos progressively.

Pricing

Apache-2.0; compute costs extra Repository code: Apache-2.0. Model weights and dependencies may have separate terms. No hosted price is estimated here. Budget for your own GPU or cloud usage after testing a representative workload.

Limitations

Headline throughput depends on high-end accelerators; low-memory offloading does not imply the same generation speed.

Read the documentation ↗

EDITORIAL VIEW

Editor's Verdict

Consider Helios if its documented workflow matches your experiment; start from the linked repository rather than an unofficial mirror.

Check the licence and run a small local evaluation before choosing it for production. No ratings or measured results are inferred from its publication.

How It Works

  • Compresses historical and noisy context while reducing sampling steps to produce long videos progressively.

What We Like

  • Publishes model variants, training code, inference scripts and a Diffusers integration for long-form generation experiments.

Current Limitations

  • Headline throughput depends on high-end accelerators; low-memory offloading does not imply the same generation speed.

Pricing & Access

  • Repository code: Apache-2.0. Model weights and dependencies may have separate terms.
  • No hosted price is estimated here. Budget for your own GPU or cloud usage after testing a representative workload.

Verification Summary

  • Official repository and licence reviewed on 2026-09-14. Video Runtime has not installed or benchmarked this project.
  • This is a source review, not verification of demo uptime, output quality or performance on your hardware.
Technical notes & official performance

Official Performance Data

  • The authors report 19.5 FPS on one H100 and about 10 FPS on one Ascend NPU. These hardware-specific figures are not site measurements.

Technical Notes

  • The repository documents base, mid and distilled checkpoints plus text-to-video and image-to-video workflows.

Sources

  1. Official GitHub repository ↗github · accessed 2026-09-14
  2. Code licence ↗github · accessed 2026-09-14
  3. Official project documentation ↗official-docs · accessed 2026-09-14

Access, stage & mechanism

These are separate source-checked facts, not a live uptime monitor. Unverified fields are left open; transport and persistent sessions do not establish how frames are generated.

Release stage
Not verified
Access mode
Not verified
Source availability
Not verified
Transport
Not verified
Interaction
Not verified
Session mode
Not verified
Generation mechanism
Not verified
Continuity method
Not verified
Licence status
Not verified
Tasks
Not classified

Read how official-source and hands-on records stay separate in our Methodology.