Exploring Multimodal AI Video Creation with VDU's Latest Model

This chapter explores the latest update to VDU's multimodal AI video model, highlighting its ability to generate unique videos by blending images of faces, outfits, and settings. Through various examples, the chapter illustrates the model's creative potential while acknowledging some imperfections in the final outputs.

Transcript

chevron_right

Play full episode

chevron_right

Transcript

Episode notes

AI NEWS: OpenAI, Google & other AI companies face potential struggles to advance their frontier AI models like Orion, but Anthropic's CEO still predicts AGI by 2027. What gives?

We discuss the growing fear that AI scaling has peaked and what’s causing the slowdown. Meanwhile, Apple makes strides in AI tech, we got our hands on Suno V4 which is *great* and China’s Deep Robotics showcases an off-road robot that scared the pants off us. Plus, NVIDIA’s new robotic advancements and Xpeng's humanoid robot reveal, and we explore how Meta’s AI chatbot gave foragers deadly advice.

IT’S NOT OVER… IT’S ONLY JUST BEGUN

Join the discord: https://discord.gg/muD2TYgC8f

AI For Humans Newsletter: https://aiforhumans.beehiiv.com/

Join our TikTok @aiforhumansshow

To book us for speaking, please visit our website: https://www.aiforhumans.show/

#ai #aitools #openai

// SHOW LINKS //

Ilya Says Scaling Is Plateau-ing

https://www.reuters.com/technology/artificial-intelligence/openai-rivals-seek-new-path-smarter-ai-current-methods-hit-limitations-2024-11-11/

OpenAI sources say training scaling is slowing down…

https://www.theinformation.com/articles/openai-shifts-strategy-as-rate-of-gpt-ai-improvements-slows?rc=c3oojq&shared=cee45715e080388f

Noam Brown on Inference Training