The Yoga of Image Generation with Stable Diffusion & ComfyUI

Unlock the potential of Stable Diffusion for controlled image generation through an engaging, hands-on session. We'll demonstrate how generative AI can craft accurate, diverse, and inclusive images of yoga poses—ideal for scenarios where stock photos or internet-sourced images are inadequate.
Using ComfyUI’s modular workflows, embeddings, inpainting, ControlNets, LoRA, and FaceID for style and pose control, you'll learn how to generate precise images with ease. From text-to-image to hybrid image-to-image workflows, we’ll explore solutions to key challenges like ensuring pose consistency and preserving identity.
The Tools-in-Action features live demonstrations, practical tips, and insights drawn from the development of YogĀrkana, a dedicated yoga website.
By the end, you'll have actionable knowledge on customizing Stable Diffusion workflows and running them locally to fulfill your creative, commercial, or inclusive design objectives.