Shypd.aiThe largest open index of AI tools
Lumiere is a space-time diffusion model by Google Research that generates realistic and coherent videos from text prompts and images. It supports various content creation tasks including video stylization and inpainting.
Trending
About
Lumiere is an innovative text-to-video diffusion model developed by Google Research, designed to synthesize videos with realistic, diverse, and coherent motion. Unlike existing video models that rely on synthesizing distant keyframes and temporal super-resolution, Lumiere employs a Space-Time U-Net architecture to generate the entire temporal duration of a video in a single pass. This approach significantly enhances global temporal consistency. Leveraging a pre-trained text-to-image diffusion model, Lumiere processes video at multiple space-time scales to produce full-frame-rate, low-resolution videos. The model excels in various content creation tasks, including text-to-video generation, image-to-video conversion, stylized generation using reference images, video stylization, cinemagraphs, and video inpainting, offering state-of-the-art results.
Capabilities
Pricing & Plans
Likely Free
Free Demo
FAQs
Trending
