HunyuanVideo (Tencent)

Leading#3 in Open sourcehigh confidence
Tencent's 13B open video model (~12.4k GitHub★) — a benchmark reference for open-source cinematic text-to-video quality.
Our read

Why it ranks #3

Approximately 12.4k GitHub stars and repeated inclusion in open-source video comparisons make HunyuanVideo a benchmark reference for large cinematic open models.

Here is the catch

very high VRAM and storage demands
slow inference on consumer hardware
complex setup compared with hosted generators

Does this well

strong cinematic detail among open models
official Tencent research release
widely supported by community workflows

Pricing

Checked by hand on 2026-07-23. Prices in this category change often — if this looks wrong, it probably is.

Key features

13B text-to-video modelImage-to-video variantsBilingual prompt encodingPublished inference and training code
Search an area, or a tool by name.