AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching

Jinshan Liu, Haoran Qin, Xiaobing Tu, Jiacheng Liu, Jiahui Hu, zhengan yan, Yukun Xie, Kerui Shen, Jinkui Ren, Yuqi Lin, Xiantao Zhang, Linfeng Zhang

ECCV 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 0 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
Use LinCa learned decomposition instead of TaylorSeer at similar caching intervalFLUX.1-dev feature caching · DrawBench (200 prompts)ImageReward: 1.0018 -> 1.0175Improved
Use LinCa instead of HyCa at higher accelerationFLUX.1-dev feature caching · DrawBench (200 prompts)ImageReward: 1.0096 -> 1.0228Improved
Use LinCa instead of TaylorSeer on Qwen-Image at N=3Qwen-Image feature caching · DrawBench (200 prompts)ImageReward: 1.0674 -> 1.2329Improved
Use LinCa instead of TaylorSeer at high speedup on Qwen-ImageQwen-Image feature caching · DrawBench (200 prompts)ImageReward: 0.7318 -> 1.0524Improved
Use LinCa instead of TaylorSeer on HunyuanVideoHunyuanVideo feature caching · VBenchVBench score (%): 79.93 -> 80.16Improved
Use LinCa instead of TaylorSeer on Qwen-Image-Edit at N=7Qwen-Image-Edit feature caching · GEdit-CN Overall ScoreOverall Score: 6.92 -> 7.45Improved
Use LinCa instead of TaylorSeer at N=9-10 on Qwen-Image-EditQwen-Image-Edit feature caching · GEdit-EN Overall ScoreOverall Score: 6.31 -> 7.40Improved
Stack LinCa on model-distilled FLUX.1-lite-8BFLUX.1-lite-8B · DrawBench (200 prompts)ImageReward: 0.8936 -> 0.9070Improved
Stack LinCa on step-distilled FLUX.1-schnellFLUX.1-schnell · DrawBench (200 prompts)ImageReward: 0.9692 -> 0.9843Improved
Stack LinCa on INT8-quantized FLUX.1-devFLUX.1-dev-int8 · DrawBench (200 prompts)ImageReward: 0.9744 -> 1.0036Improved
Use invertible network instead of non-invertible learnable MLP for decomposition (ablation)LinCa · FLUX.1-dev and Qwen-Imagegeneration qualityImproved
Use learnable decomposition instead of non-learnable strategies (ablation)LinCa · FLUX.1-dev and Qwen-Imagegeneration qualityImproved

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