Overview
Video Latent Diffusion Models (Video LDMs) are a type of generative model that enables high-quality video synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space.
Temporal Video Generation
Video LDMs generate temporally coherent videos by modeling sequences of latent variables corresponding to the video frames.
High-Resolution Video Synthesis
Video LDMs can generate high-resolution videos by leveraging spatial diffusion model upsamplers and temporally aligning them for video upsampling.
Personalized Video Generation
Video LDMs can generate personalized videos by inserting the temporal layers that were trained for our Video LDM for text-to-video synthesis into image LDM backbones that we previously fine-tuned on a set of images following DreamBooth.
Long Video Generation
Video LDMs can generate long videos by applying our learnt temporal layers convolutionally in time.
Get started
- Open the official website and confirm the service is available in your region.
- Check the current plan, usage limits and terms for your intended use.
- Try a small task with sample data before committing to a paid plan.
Editorial note
Pricing checked: Sep 20, 2026. Official website is active. Please verify current pricing and terms directly on the official site.
Record updated: Sep 20, 2026
Suggest a correction
