Diffusion models (DDPM): from noise to images
How denoising diffusion probabilistic models (DDPM) add noise step by step, learn to predict it with a simple MSE loss, and generate by denoising.
Part of Generating images.
Read next
- Classifier-free guidance (CFG) for diffusion models
How classifier-free guidance (CFG) makes diffusion models follow a prompt: drop it in training, then step past the prompted noise guess by a guidance scale w.
Related
- U-Net: skip connections for image segmentation
How the U-Net segments images: an encoder shrinks to see what is there, a decoder grows back, and skip connections copy fine detail across.