Linoy Tsaban is an ML engineer at Hugging Face, working on Art & Creativity. Linoy did her BSc and MSc in computer science at the Hebrew University, with a thesis focusing on ML applications for cancer genetics. With the rise of diffusion models and their applications for creative use cases, she became increasingly fascinated with the world of creative AI and now explores this domain as an AI artist and machine learning engineer.
In this talk, we delve into the world of text-to-image diffusion models, focusing on their recent surge in popularity and their application to real image editing. Acknowledging the shortcomings of current image-to-image methods, we introduce LEDITS++, an efficient, versatile, and precise textual image manipulation technique for real-image editing. Our approach features a novel inversion method requiring no tuning or optimization, supporting multiple simultaneous edits across diverse architectures. We incorporate a unique implicit masking technique to constrain edits to relevant image regions. The talk will include a live demo showcasing the editing properties of LEDITS++ in advancing text-guided image manipulation.
| 8:45 | Reception |
|---|---|
| 9:30 | Opening remarks by WiDS TLV ambassadors Noah Eyal Altman, Or Basson, and Nitzan Gado |
| 9:45 | Dr. Aya Soffer, IBM: "Putting Generative AI to Work: What Have We Learned So Far?" |
| 10:15 | Prof. Reut Tsarfaty, Bar-llan University: "Will Hebrew Speakers Be Able to Use Generative AI in Their Native Tongue?" |
| 10:45 | Poster Pitches |
| 10:55 | Break |
| 11:10 | Lightning talks |
| 12:30 | Lunch & poster session |
|---|---|
| 13:30 | Roundtable session & poster session |
| 14:15 | Roundtable closing |
| 14:30 | Break |
| 14:40 | Naomi Ken Korem, Lightricks: "Mastering the Art of Generative Models: Training and Controlling Text-to-Video Models" |
| 15:00 | Dr. Yael Mathov, Intuit: "Surviving the AI-pocalypse: Your Guide to LLM Security" |
| 15:20 | Closing remarks |
| 15:30 | The end |