1 个仓库
Awesome GitHub RepositoriesSingle-Step Sampling
Techniques that allow a generative model to produce an image in a single sampling step.
Distinct from Low-Step Sampling: Distinct from Low-Step Sampling: specifically targets the capability of producing a final image in exactly one step.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Single-Step Sampling. Refine with filters or upvote what's useful.
Awesome Single-Step Sampling 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/consistency_models
openai/consistency_models
6,492在 GitHub 上查看This project is a framework for training and sampling generative models designed to produce high-quality images in few steps. It provides implementations for image generation models that transform random noise into structured visual data through an optimized sampling process. The system specializes in accelerating image generation through consistency distillation and consistency training. It includes tools to transform pre-trained diffusion models into faster versions by distilling knowledge from a teacher model into a student model, as well as methods to train consistency models from scratch
Enables the production of high-quality images in a single step by mapping ODE trajectories back to the origin.
Python
