Runway’s model promises cinematic-quality output with precise control, aiming to boost creative possibilities for content creators and enterprises alike.
- Runway has refined both pre-training and post-training methods to optimize efficiency.
- The model currently tops the Artificial Analysis Text-to-Video benchmark with 1,247 Elo points.
Runway, an artificial intelligence startup, unveiled its latest video generation model, Gen-4.5, on Monday, claiming it as the most advanced video AI system to date.
The model promises cinematic-quality output with precise control, aiming to boost creative possibilities for content creators and enterprises alike.
Gen-4.5 Advances Video AI
Building on its previous models, including the Gen-1 launched two years ago, Runway has refined both pre- and post-training methods to optimize efficiency and output quality.
The model currently tops the Artificial Analysis Text-to-Video benchmark with 1,247 Elo points, surpassing competitors in fidelity, consistency, and controllability. According to a CNBC report, Runway’s model tops models from Google and OpenAI in terms of translating written prompts into high-definition video sequences.
Get updates to this developing story directly on Stocktwits.<