AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval

Kexun Zhang, Xianjun Yang, William Yang Wang, Lei Li

ICML 2023 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add ReDi top-2 retrievalPNDM · MS-COCO val, NFE 20FID: 0.274 -> 0.255Improved
add ReDi top-2 retrievalDPM-Solver · MS-COCO val, NFE 10FID: 0.268 -> 0.261Improved
use top-2 instead of top-1 retrieved neighbors (ablation)ReDi on PNDM · MS-COCO val, NFE 30FID: 0.264 -> 0.247Improved
add ReDi top-1 retrievalPNDM · MS-COCO val, NFE 40FID: 0.262 -> 0.262No clear effect
use trajectory samples instead of CLIP embeddings as retrieval key (ablation)ReDi · MS-COCO val, NFE 30FID: 0.2784 -> 0.2643Improved
use trajectory samples instead of CLIP embeddings as retrieval key (ablation)ReDi · MS-COCO val, NFE 40L2 distance to true value: 9.03 -> 7.95Improved
add retrieval instead of vanilla skipping from k to v (ablation)ReDi · PNDM k=40, v=20FID: 1.58 -> 0.267Improved
use conditional x_T initial sample instead of unconditional for knowledge base (ablation)ReDi · PNDM, NFE 20-40FID: 0.268 -> 0.265No clear effect
change guidance scale away from the 7.5 used to build the knowledge base (ablation)ReDi · MS-COCO valFID: 0.264 -> 0.271Hurt
shrink knowledge base size from 50K to 20K (ablation)ReDi · MS-COCO val, PNDMFIDHurt
increase gap k-v with k=40 (v from 35 to 25) (ablation)ReDi · MS-COCO val, PNDMFIDHurt
lower key step k from 40 to 20 with k-v=15 (ablation)ReDi · MS-COCO val, PNDMFIDHurt

Later papers that compared with this method

3 later accepted papers report ReDi as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy