Dhruv Nair

Dhruv Nair

Machine Learning Engineer

Hugging Face

Dhruv Nair is a core maintainer for the Diffusers library at Hugging Face, where he works on democratizing access to diffusion models. He is a strong believer in the open development of AI, and is passionate about generative media and building tools for creators.

AI doesn’t have to replace human creativity - it can enhance it. In this session, we explore how to build AI agents that act as collaborators in creative workflows, from visual design to multimedia storytelling. You’ll learn how to architect systems that support ideation, iteration, and refinement alongside human input. 

We’ll dive into how the ReAct agent framework can be tailored for creative tasks, enabling intelligent planning and feedback-driven media generation. Learn to integrate open-source tools like Stable Diffusion, Flux, LoRAs, and IPAdapters to turn creative briefs into coherent, high-quality visual outputs.

But creating is only half the battle, we’ll also show how to build effective feedback loops using techniques like aesthetic scoring and user-in-the-loop editing to improve outputs in real time. Expect hands-on code, real-world examples, and practical takeaways to bring human-AI co-creation to life in your own design, content, or media pipeline.

Read More

Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance

Read More

Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance

Read More
Book tickets View all speakers

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details