Open AI Announces Sora, an AI Text to Video Model
February 16th, 2024Up until now, text to video AI has been most effective for generating surreal and hilarious nightmare fuel. Morphing humanoids and other bizarre hallucinations make for a sort of weird comedy gold:
OpenAI’s Sora produces much more impressive results.
While many of the example videos contain anomalies, these tend be far less glaring than with previous systems.
It’s hard to imagine where this will be in five or ten years…
The potential for PSYOP is unlimited.
Via: OpenAI:
We’re teaching AI to understand and simulate the physical world in motion, with the goal of training models that help people solve problems that require real-world interaction.
Introducing Sora, our text-to-video model. Sora can generate videos up to a minute long while maintaining visual quality and adherence to the user’s prompt.
More: OpenAI Collapses Media Reality with Sora, a Photorealistic AI Video Generator
