HyperFlow H3

A data-free flow self-distillation technology built on MiniMax H3.

  • Lower inference cost
  • Frontier model quality
  • Open source

Ranked #2 on Artificial Analysis Video Editing v1.1 leaderboard, Nov 2026.

Over#20,024downloads

Artificial Analysis Video Editing v1.1 leaderboard, with HyperFlow H3 in second place

Introducing HyperFlow H3

See it in action

Showing Camera Control

How it works

  1. The model generates its own candidate videos. Filters them for quality. Self-distills from the ones that pass.

  2. No external data. No human labels. The model trains itself with its own outputs.

  3. This is the self-distillation component of RSI (Recursive Self-Improvement), our training paradigm for video models.

  4. HyperFlow H3 also supports NVIDIA's Sol-Attn sparse-attention kernel, delivering up to 13% faster H200 generation than dense attention.

The HyperFlow series

The series now includes three releases, each addressing a different constraint. HyperFlow reduced the cost of training. HyperFlow Infinity extended the length of a single generation. HyperFlow H3 Flash reduces latency until generation and playback run at the same speed.

HyperFlow Infinity

A recursive agent harness for infinite video generation.

View Infinity

Infinity and HyperFlow share the same weights. One download works for both.

HyperFlow H3 — Data-Free Flow Self-Distillation on MiniMax H3 | Video Rebirth