Conditionally licensed video models
32 in the catalogue today. Every one with what it costs, who sells it and where it stands.
Models that generate moving footage, most of them now with sound. Priced by the second of output, sometimes doubled for higher resolution, which makes this the most expensive thing in the catalogue to experiment with — a minute of 1080p can cost more than a million tokens of text. Check the maximum clip length and whether it will continue from an image you supply.
Weights you can download, under a licence that asks for something in return: an acceptable-use policy, a naming requirement, a revenue ceiling above which you must ask, a restriction on training other models. The Llama and Gemma families are the familiar cases. Read the actual licence before you build on one of these — the condition is usually easy to meet and occasionally fatal, and which it is depends on your product rather than on the model.
- AnimateDiff-LightningByteDance
- CogVideoX-5bZ.ai
- CogVideoX-5b-I2Vzai-org
- CogVideoX1.5-5B-SATzai-org
- Cosmos-1.0-Diffusion-7B-Text2WorldNVIDIA
- Cosmos3-Super-Image2VideoNVIDIA
- FastHunyuanFastVideo
- FastVideo-FastH3-4-step-Preview-v1-VSA-DataFreeFastVideo
- Hotshot-XLhotshotco
- HunyuanVideoTencent Hunyuan
- HunyuanVideo-1.5Tencent Hunyuan
- HunyuanVideo-I2VTencent Hunyuan
- HunyuanWorld-VoyagerTencent Hunyuan
- Hy-OmniWeavingTencent Hunyuan
- Hy-WorldPlayTencent Hunyuan
- JoyAI-Echojdopensource
- LTX-2LTX.io
- LTX-2.3LTX.io
- LTX-2.5LTX.io
- LTX-VideoLTX.io
- MiniMax-H3MiniMax3rd of 32$0.04per image, 2k lane1 selling
- MiniMax-H3-Acc-LoRAsAlibaba-PAI
- MiniMax-H3-Fun-Controlnet-UnionAlibaba-PAI
- Minimax-H3-fl2va-ref2va-hybrid-modelssmhfacct
- TemporalDiffCiaraRowles
- pyramid-flow-sd3rain1011
- stable-video-diffusion-img2vidStability AI
- stable-video-diffusion-img2vid-xtStability AI
- stable-video-diffusion-img2vid-xt-1-1Stability AI
- stable-virtual-cameraStability AI
- sv3dStability AI
- vdn-minimax-h3OpenVDN