Image Generation AI Workshop: Diffusion Model Architecture and Beyond - Deep Dive with a Diffusion Model Pioneer
Stop generating images that make you cry—dive deep into diffusion models with a former Diffusion researcher from Stability.AI, the company that created Stable Diffusion!
From the architecture behind Transformers (like ChatGPT) to cutting-edge image-based models like Stable Diffusion and Flux, these workshops are designed to deepen your understanding of generative AI.
Workshop 1: From Neural Net to Diffusion Models | Sep 17th 5pm PST (It is finished, see the recording and highlights here: https://share.descript.com/view/XqH2LxoX4eM):
• Transformer Architecture in Vision Context: The history of ML architecture that leads to the Diffusion Model, such as GAN, CLIP, CNN, and Transformer models.
• Project Walk-through with Code: Vision Transformer
Workshop 2: Diffusion Model Architecture and Beyond | Sep 24th 5pm PST (https://lu.ma/onfbp0kw):
• Stable Diffusion & Flux Architecture: Exploring the main algorithms and architecture behind Diffusion Models and the flow of information within them.
• Staying Up-to-date on AI Research: Resources for keeping upto date with latest Image Genration Model Research like a Researcher.
• Beyond Diffusion Models: Open Problems and Trends within the field of Image Generation
• Project Walk-through with Code: Diffusion Model Breakdown.
Speakers:
• Shahbuland Matiana, Speaker:
Machine Learning Researcher at Synth Labs, formerly Machine Learning Researcher at StabilityAI, the company behind Stable Diffusion. Specializing in diffusion models and large language models. Known for simplifying complex AI research.
• Ti Guo, Facilitator:
Gen AI Data Scientist at SparkCraft, formerly Gen AI Data Scientist at IBM, into simplifying complex technical AI concepts for all audiences.
Don’t miss this chance to enhance your knowledge of generative AI! We look forward to seeing you there!