Open video generation models

Open text-to-video and image-to-video models — heavier, but runnable on a rented GPU. Every one is downloadable and runs on your own machine or a rented GPU — honest, $0-markup.

Wan2.2 T2V-A14B — Text → video, Alibaba (Wan-AI) · ~24 GB VRAM · rent $0.49/hr · commercial OK
Wan2.2 I2V-A14B — Image → video, Alibaba (Wan-AI) · ~24 GB VRAM · rent $0.49/hr · commercial OK
HunyuanVideo — Text → video, Tencent · ~45 GB VRAM · rent $1.39/hr · non-commercial
Wan2.2 TI2V-5B — Text → video, Alibaba (Wan-AI) · ~8.0 GB VRAM · rent $0.26/hr · commercial OK
LTX-Video (13B) — Text → video, Lightricks · ~13 GB VRAM · rent $0.26/hr · commercial OK
CogVideoX-5B — Text → video, Zhipu AI / THUDM · ~5.0 GB VRAM · rent $0.26/hr · non-commercial
Stable Video Diffusion (img2vid-XT) — Image → video, Stability AI · ~16 GB VRAM · rent $0.26/hr · commercial OK
Wan2.1 T2V-1.3B — Text → video, Alibaba (Wan-AI) · ~8.0 GB VRAM · rent $0.26/hr · commercial OK
AnimateDiff (motion adapter) — Text → video, Yuwei Guo (guoyww) · ~8.0 GB VRAM · rent $0.26/hr · commercial OK
Mochi 1 (preview) — Text → video, Genmo · ~24 GB VRAM · rent $0.49/hr · commercial OK
Open-Sora 2.0 — Text → video, HPC-AI Tech · ~24 GB VRAM · rent $0.49/hr · commercial OK
CogVideoX-2B — Text → video, Zhipu AI / THUDM · ~4.0 GB VRAM · rent $0.26/hr · commercial OK
Allegro — Text → video, Rhymes AI · ~10 GB VRAM · rent $0.26/hr · commercial OK
Pyramid Flow (SD3) — Text → video, Pyramid Flow team · ~12 GB VRAM · rent $0.26/hr · commercial OK

Other media types

Image · Voice & Audio · Multimodal / Omni · All media