// ✦ Diffusion, Flow Matching & Generative Models
Consistency Models
Maps any point on a trajectory directly to its endpoint for one-step generation.
一致性模型 2023 Advanced extended
IN PLAIN WORDS
Enforce consistent outputs along a denoising trajectory, so any noisy input maps to a clean image in one step; trained by distillation or from scratch. Basis of LCM-style fast generators.
Used in: LCM, real-time image generation
TIMELINE · prerequisites → this → what builds on it
01Original paper
Consistency Models
Yang Song, Prafulla Dhariwal, Mark Chen, et al. · 2023
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Learn first
Then you can learn
- Nothing in the atlas builds on it yet
Related:Rectified Flow
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
Official docs
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
consistency-models)