Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore cutting-edge developments in computer vision through this advanced graduate-level course focusing on modern generative AI and diffusion models. Begin with foundational concepts including transformers and early breakthrough models like DALL-E and CLIP, then dive deep into the mathematical foundations and practical applications of diffusion models. Master state-of-the-art text-to-image synthesis techniques through comprehensive coverage of GLIDE, DALL-E-2, Stable Diffusion, and Imagen, while learning specialized applications including DreamBooth for personalized generation and human motion modeling. Examine advanced topics such as analytic denoising probabilistic models, person image synthesis, object detection with diffusion models, and cascaded approaches for high-fidelity generation. Discover vector quantized diffusion models, image super-resolution techniques, and semantic segmentation applications through SegDiff. Investigate video generation capabilities for long sequences and explore guided image synthesis using stochastic differential equations, concluding with inpainting techniques through RePaint methodology.
