We provide visual examples for text-to-video generation on our ultra-compact latent space with 32x temporal compression and the videos are generated at the resolution of 192x320.
The early stage results suggest that we could generate videos with plausible content with 5x reduction in the number of latent frames compared to current state-of-the-art MAGVIT-v2.
Note: Our goal is not to compete with the state-of–the-art text-to-video generation method, but just to show that our ultra-compact latent space is compatible for text-to-video generation.
Note: Hover over the text to see the full prompt.
A young woman with vibrant red hair, adorned with a whimsical leafy crown...
A young woman with vibrant red hair, adorned with a whimsical leafy crown...
A cinematic documentary hand held close up of a woman standing...
A cinematic documentary hand held close up of a woman standing...
Close up shot of a woman, police lights flashing in background...
Close up shot of a woman, police lights flashing in background...
A slow cinematic push in on an ostrich standing in a 1980s kitchen.
A slow cinematic push in on an ostrich standing in a 1980s kitchen.
A cat wearing sunglasses and working as a lifeguard at a pool.
A cat wearing sunglasses and working as a lifeguard at a pool.
A person sitting on a bed looking at a spectacular night sky full of galaxies...
A person sitting on a bed looking at a spectacular night sky full of galaxies...
A sheep behind a fence looking at the camera.
A sheep behind a fence looking at the camera.
A side view of an owl sitting in a
field.
A side view of an owl sitting in a
field.
A stunning aerial drone footage time lapse of El Capitan in...
A stunning aerial drone footage time lapse of El Capitan in...
Time lapse at the snow land with aurora in the sky, 4k, high resolution.
Time lapse at the snow land with aurora in the sky, 4k, high resolution.
A beautiful sunrise on mars. High definition, timelapse, dramatic colors.
A beautiful sunrise on mars. High definition, timelapse, dramatic colors.
A big moon rises on top of Toronto
city.
A big moon rises on top of Toronto
city.
Milk dripping into a cup of coffee, high definition, 4k.
Milk dripping into a cup of coffee, high definition, 4k.
Beer pouring into glass, low angle video shot.
Beer pouring into glass, low angle video shot.
Melting pistachio ice cream dripping down the cone.
Melting pistachio ice cream dripping down the cone.
Chocolate syrup pouring on a vanilla ice cream.
Chocolate syrup pouring on a vanilla ice cream.
A dramatic close-up shows an elderly man in harsh red light...
A dramatic close-up shows an elderly man in harsh red light...
Create a high-quality, realistic video portrait of an android...
Create a high-quality, realistic video portrait of an android...