Open text-to-video and image-to-video models (2B under Apache-2.0, 5B under CogVideoX license)
CogVideoX (Zhipu) is listed under AI Video Generation, in the Content & Media Generation category on Flocci AI Tools. Open text-to-video and image-to-video models (2B under Apache-2.0, 5B under CogVideoX license). It is free, with no paid plan attached, and it lives at github.com.
CogVideoX (Zhipu) is listed as fully free — there is no paid tier attached to it in the catalog. That makes it one of the 399 entries on Flocci AI Tools with no upgrade path built in.
CogVideoX (Zhipu) does 3 things the catalog singles out: Open text-to-video and image-to-video models (2b under apache-2.0, 5b under cogvideox license); cogkit toolkit for fine-tuning cogvideox and cogview4; free hugging face and modelscope space demos.
Genmo (Mochi 1) is the closest free alternative: it sits in the same AI Video Generation sub-category and is free. HunyuanVideo (Tencent), HunyuanVideo 1.5 and Kandinsky 5.0 also start free. The full list is on the alternatives page.
See the full list →