a16z Podcast
Text to Video: The Next Leap in AI Generation
General Partner Anjney Midha explores the cutting-ed...
more
Dec 20 2023 32m
Chapter 1 2 mins
Text to Video: The Next Leap in AI GenerationChapter 2 1 min
The Stable Diffusion backstoryChapter 3 1 min
Diffusion vs autoregressive modelsChapter 4 3 mins
The benefits of single step samplingChapter 5 2 mins
Why generative video?Chapter 6 1 min
Understanding physics through AI videoChapter 7 3 mins
The challenge of creating generative videoChapter 8 2 mins
Data set selection and trainingChapter 9 1 min
Structural consistency and 3D objectsChapter 10 1 min
Incorporating LoRAsChapter 11 2 mins
How should creators think about these tools?Chapter 12 1 min
Open challenges in video generationChapter 13 6 mins
Infrastructure challenges and future research