Sayak Paul
Hi there 👋. I am Sayak Paul (সায়ক পাল). I work on 🧨 diffusion models at Hugging Face. Know more about me from here. I maintain a Google Doc answering some FAQs at length. You can check it out here.
My external articles and other publishing engagements (like books, liveProjects, etc.) are listed here. Decks from my speaking engagements are listed here. A detailed account of the things that are not directly available from the top navbar (interviews, talks etc.) can be found here.
The structure of this website is inspired by Omar’s site.
News
- Hila Chefer and I presented our tutorial All Things ViTs: Understanding and Interpreting Attention in Vision at CVPR 2023. Check out the website for a recording, code samples, slides, and more.
- New work on accelerating SDXL by 3x with pure PyTorch: Accelerate inference of text-to-image diffusion models. Post is live on the PyTorch blog too.
- New podcast with Varun Mayya: Conversation with a Hugging Face developer.
- New work on implementing the CMMD metric in PyTorch. Check it out here.
- New paper in collaboration with Junsong Chen, Yue Wu, Simian Luo, Enze Xie, Ping Luo, Hang Zhao, and Zhenguo Li: PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models.
To know about my projects, please refer to my GitHub profile.
Apart from the blogs here, I try to contribute to other platforms in the form of writing. Please refer here for more details.