2 Repos
Awesome GitHub RepositoriesClassifier-Guided Methods
Guides the reverse diffusion process by injecting classifier gradients to steer sample quality toward higher fidelity.
Distinct from Diffusion Sampling Methods: Distinct from general Diffusion Sampling Methods: specifically uses classifier gradients for guidance, not numerical solvers or discretization methods.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Classifier-Guided Methods. Refine with filters or upvote what's useful.
Awesome Classifier-Guided Methods GitHub Repositories
Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
- openai/guided-diffusion
openai/guided-diffusion
7,395Auf GitHub ansehenThis 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 classifier-guided diffusion sampling that injects classifier gradients to steer sample quality toward higher fidelity.
Python - openai/glide-text2im
openai/glide-text2im
3,688Auf GitHub ansehenGLIDE is a generative model designed for text-to-image synthesis, image editing, and the contextual filling of masked image regions. It uses a guided diffusion process to transform random noise into high-resolution imagery that aligns with descriptive text prompts. The system provides specialized capabilities for modifying existing visuals, including the ability to alter specific image elements and iteratively refine selected regions through text-driven guidance. It also functions as an inpainting tool, filling missing or masked sections of an image with new content that blends naturally with
Incorporates a separate classifier to guide the diffusion sampling process for better text alignment.
Python
