Open-Sora

HPC-AI Tech
class A live

Open-source 11B diffusion text/image-to-video model; Apache-2.0 weights, self-host, up to 768px and ~5s, no native audio.

Layer 1 — factual axes

API & price self-host only official source ↗ 2026-07-04
Max output 768px · ~5s official source ↗ 2026-07-04
Native audio no official source ↗ 2026-07-04
Weights open · Apache-2.0 official source ↗ 2026-07-04
Free tier open self-host (free Gradio demo on HF) official source ↗ 2026-07-04

Layer 2 — output quality

No independent measure yet. We publish a quality figure only when a named external benchmark ranks this model — we don’t invent one.

Eligible for Best freeOpen-weights

Open-source 11B diffusion text/image-to-video model; Apache-2.0 weights, self-host, up to 768px and ~5s, no native audio.

Data as of 2026-07-04 · verified 2026-07-04. One ruler for all tools. How we measure ↗