1 个仓库
Awesome GitHub RepositoriesClassifier-Guided Variants
A framework that steers diffusion model sampling using a classifier to produce images with higher fidelity and controlled attributes.
Distinct from Diffusion Model Frameworks: Distinct from general Diffusion Model Frameworks: specifically includes classifier guidance for steering sampling, not just training and sampling.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Classifier-Guided Variants. Refine with filters or upvote what's useful.
Awesome Classifier-Guided Variants GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- openai/guided-diffusion
openai/guided-diffusion
7,395在 GitHub 上查看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
Provides a classifier-guided diffusion framework that steers sampling using a classifier for higher fidelity and controlled attributes.
Python
