1 Repo
Training a diffusion model from scratch on a dataset using distributed processes and adjustable settings.
Distinct from Diffusion Model Training: Distinct from general Diffusion Model Training: specifically covers distributed training with gradient accumulation, not the general training process.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Distributed Training. Refine with filters or upvote what's useful.
This is a classifier-guided diffusion framework for high-fidelity image generation. It implements a cascaded diffusion pipeline that chains a base diffusion model with a dedicated upsampler to progressively increase image resolution in stages, and uses classifier-guided diffusion sampling to steer the reverse diffusion process toward higher-quality outputs. The framework provides tools for training diffusion models from scratch using distributed processes with gradient accumulation, as well as training classifier models that provide gradient-based guidance during sampling. It supports both un
Trains a diffusion model from scratch on a dataset using distributed processes and adjustable settings.