Video generation research and development is moving forward strongly and expanding with new entrants. Powerful new text-to-video (T2V) models have emerged in recent months following the first to market models from Runway and Pika Labs and the seismic introduction of OpenAI’s Sora in February.
How to Use OpenAI Sora Video Generator 2024 (AI Text to Video)
The latest entrant is Veo, Google DeepMind’s most powerful video generation model, unveiled last week at the Google I/O developer conference. More such models are coming from developers including Irreverent Labs.
Google took a similar approach to Veo as it did for OpenAI with Sora. Initially, Veo was made available as a research preview to a number of artists, including Donald Glover and his creative agency Gilga. This allowed them to gather initial feedback on the model’s capabilities and limitations before expanding it to other groups.
Both companies are reportedly involving the creative community in Hollywood. In March, OpenAI CEO Sam Altman met with executives at major studios including Paramount, Warner Bros. and Universal, and several A-list directors were among Sora's early testers.
