Hemm: Holistic Evaluation of Multimodal Generative Models

Join Anish Shah, ML Engineer at Weights & Biases, for an in-depth session on fine-tuning and evaluating multimodal generative models. This talk delves into advanced methodologies for optimizing text-to-image diffusion models, focusing on enhancing image quality and improving prompt comprehension. Learn how to leverage Weights & Biases for efficient experiment tracking and utilize Weave for tracking and evaluating LLM applications. The session introduces Hemm, a comprehensive library for benchmarking text-to-image diffusion models on image quality and prompt comprehension, integrated with Weights & Biases and Weave. By the end, attendees will be equipped with cutting-edge tools and techniques to elevate their multimodal generative models.