Veo
Free while signed in. Answers cite the passages they came from.
Paper preview
The curator’s take
Google Deepmind’s most capable video generation model generates high-quality, 1080p resolution videos beyond 1 minute; it supports masked editing on videos and can also generate videos with an input image along with text; the model can extend video clips to 60 seconds and more while keeping consistency with its latent diffusion transformer.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack