AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

NAMI: Efficient Image Generation via Bridged Progressive Rectified Flow Transformers

Yuhang Ma, Bo Cheng, Shanyuan Liu, Hongyi Zhou, Liebucha Wu, Dawei Leng, Yuhui Yin

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling

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
split flow by resolution and partition the model into progressive stagesNAMI-2B vs FLUX-based 2B · 1024x1024 inferenceinference time (s): 8.47 -> 2.98Improved
add piecewise flow only (ablation)NAMI at 1024 · 1024 inference timeinference time reduction: 53.01% reductionImproved
add model partitioning on top of piecewise flow (ablation)NAMI at 1024 · 1024 inference timeinference time reduction: further 11.81%Improved
use multi-resolution NAMI training instead of FLUX-based trainingNAMI-0.6B · 256 res trainingFID: 9.76 -> 8.9293Improved
add model partitioning on top of flow piecewise (ablation)NAMI-0.6B · 256 and 512 resFID / CLIPNo clear effect
replace Pyramid Flow renoising with BridgeFlow (ablation)NAMI-0.6B · 256 resFID: 9.8231 -> 8.9293Improved
replace BridgeFlow with Upsample + MLP (ablation)NAMI-0.6B · 256 resFID: 8.9293 -> 9.0842No clear effect
replace BridgeFlow with Pixel Shuffle + CNN (ablation)NAMI-0.6B · 256 resFID: 8.9293 -> 8.8975No clear effect
assign too few layers to the low-resolution stage (ablation)NAMI-0.6B · 512 resFID / CLIPHurt
add more layers to low-resolution stage beyond a point (ablation)NAMI-0.6B · 512 resFID / CLIPNo clear effect
skew time windows toward low or high stages instead of uniform (ablation)NAMI-0.6B · flow window ratio ablationFID / CLIPNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

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