Alibaba has released Wan2.7-Video – a video generation model that gives users control over the entire video creation process, from script to final edit.
Video generation is one of the fastest-growing fields in AI. In just the last couple of years, text-to-video tools have evolved from curious clips with blurry faces to quite convincing short scenes. And this progress continues: Wan 2.7, a suite of four models each responsible for a specific type of video task, recently became available on the Together AI platform.
Google has updated Vids: the editor now offers free video and music generation based on the Veo 3.1 and Lyria 3 AI models.
Google has launched Veo 3.1 Lite – a lightweight version of its video generation model that is significantly more affordable to use.
OpenAI has explained how the safety system in the Sora video generator and its associated application works – from moderation to digital credentials on content.
Runway has released its 'Characters' tool, which allows you to maintain a character's appearance across different scenes, ensuring they remain recognizable.
Pruna AI has introduced P-Video – a video generation service that prioritizes speed and low cost compared to its competitors.
The SGLang team has released a new system to accelerate video generation, featuring support for long videos and real-world optimizations for high-load environments.
An MIT team has developed a method for generating 2K video that runs at the same speed as standard 720p generation, utilizing a two-stage processing scheme.