CogVideo / CogVideoX (Zhipu)

Leading#4 in Open sourcehigh confidence
Apache-2.0 CogVideoX (~12.9k GitHub★) — loads natively in HF Diffusers, strong prompt following and smooth frames; a go-to for developers.
Our read

Why it ranks #4

About 12.9k GitHub stars, Apache-2.0 licensing and first-class Diffusers support give CogVideoX unusually strong developer adoption in this cohort.

Here is the catch

large models still require significant VRAM
short clips and limited native editing controls
visual quality varies with quantization and hardware settings

Does this well

permissive license and mature developer tooling
good prompt following for an open model
easier integration through Hugging Face

Pricing

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

Key features

Text and image-to-video modelsDiffusers integrationQuantized and memory-saving inferenceFine-tuning support
Search an area, or a tool by name.