Research map / Image generation / Fast diffusion sampling
Phase-wise Velocity Distillation: Towards Effective Image Generation with A Single NFE
Zhen Guo, Rongyuan Wu, Qiaosi Yi, Chenxi Xie, Xinyu Wei, Lei Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes phase-wise velocity distillation to make a diffusion image generator produce high-quality images in a single function evaluation (NFE).
Problem
Achieving high-quality image synthesis from diffusion models under a single NFE budget is hard because a single student must resolve both global structure and fine details in one forward pass.
Approach
Exploits the coarse-to-fine progression of diffusion by distilling different phases of the velocity field separately, rather than forcing one student to learn all phases jointly in one pass.
Closest papers by meaning
- Simple and Fast Distillation of Diffusion Models (NeurIPS 2024 · similarity 0.90)
- One-step Diffusion with Distribution Matching Distillation (CVPR 2024 · similarity 0.90)
- PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future Scores (ICLR 2025 · similarity 0.89)
- Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation (ICML 2024 · similarity 0.89)
- Diffusion Time-step Curriculum for One Image to 3D Generation (CVPR 2024 · similarity 0.89)
- Diffusion Model is Effectively Its Own Teacher (CVPR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
