"In a blog post on Monday, Runway says its Gen-4.5 model can produce "cinematic and highly realistic outputs," potentially making it even more difficult to distinguish between what's real and what's AI. "Gen-4.5 achieves unprecedented physical accuracy and visual precision," Runway's announcement says. It adds that the new AI model is better at adhering to prompts, allowing it to produce detailed scenes without compromising video quality. Runway says that AI-generated objects "move with realistic weight, momentum and force," while liquids "flow with proper dynamics.""
"There are still some limitations, though, as the model may experience issues with object permanence and causal reasoning, meaning effects may happen before the cause, such as a door opening before someone uses a handle. OpenAI highlighted upgrades to physics with the release of its Sora 2 text-to-video model in September, with Sora head Bill Peebles saying, "You can accurately do backflips on top of a paddleboard on a body of water, and all of the fluid dynamics and buoyancy are accurately modeled.""
Gen-4.5 produces cinematic and highly realistic outputs with unprecedented physical accuracy and visual precision. The model adheres better to prompts, enabling production of detailed scenes without compromising video quality. AI-generated objects move with realistic weight, momentum, and force, while liquids flow with proper dynamics. The model is rolling out gradually to users and offers the same speed and efficiency as its predecessor. Remaining limitations include issues with object permanence and causal reasoning, where effects can precede causes. Competing work on physics in text-to-video models also reproduces accurate fluid dynamics and buoyancy for lifelike movement. Photorealistic visuals can appear indistinguishable from real-world footage.
Read at The Verge
Unable to calculate read time
Collection
[
|
...
]