Towards Efficient Diffusion-based Image Generation
Date:
Internal Technical Talk of NAVER Cloud
Recent advancements in image generation models have brought significant transformations to the field of image generation. To enhance the expressive power of generated images, the parameter sizes and computational demands of these models continue to grow rapidly.
In this seminar, Dong-Hyun Hwang from the Hyperscale AI Model101 team will provide an in-depth exploration of Stability AI’s latest models, including Stable Cascade and Stable Diffusion 3. The session will focus on the efficient inference methodologies of diffusion-based models, which offer superior expressive capabilities compared to their predecessors, and will discuss future directions for advancements in this domain.