Show HN: Infinity – Realistic AI characters that can speak
Analysis
Infinity AI has developed a video diffusion transformer model focused on generating realistic, speaking AI characters. The model is driven by audio input, allowing for expressive and realistic-looking characters. The article provides links to examples and a way for users to test the technology by describing a character and receiving a generated video.
Key Takeaways
- •Infinity AI has developed a video diffusion transformer model for generating realistic, speaking AI characters.
- •The model is driven by audio input.
- •Users can test the technology by describing a character and receiving a generated video.
““Mona Lisa saying ‘what the heck are you smiling at?’”: <a href="https://bit.ly/3z8l1TM" rel="nofollow">https://bit.ly/3z8l1TM</a> “A 3D pixar-style gnome with a pointy red hat reciting the Declaration of Independence”: <a href="https://bit.ly/3XzpTdS" rel="nofollow">https://bit.ly/3XzpTdS</a> “Elon Musk singing Fly Me To The Moon by Sinatra”: <a href="https://bit.ly/47jyC7C" rel="nofollow">https://bit.ly/47jyC7C</a>”