AI Paper Atlas

Research map / Video / Video generation

Lay2Story: Extending Diffusion Transformers for Layout-Togglable Story Generation

Ao Ma, Jiasong Feng, Ke Cao, Jing Wang, Yun Wang, Quanwei Zhang, Zhanjie Zhang

ICCV 2025 · Video › Video generation · approach: Diffusion-based human image animation · 3 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 subject branch (ablation)Lay2Story · Lay2Story-BenchFID: 110.58 -> 26.71Improved
add subject branch (ablation)Lay2Story · Lay2Story-BenchRecall@1: 0.1733 -> 0.7012Improved
add reference image concatenation (ablation)Lay2Story · Lay2Story-BenchFID: 50.27 -> 26.71Improved
add reference image concatenation (ablation)Lay2Story · Lay2Story-BenchHuman preference: 0.4781 -> 0.7561Improved
add masked 3D self-attention (ablation)Lay2Story · Lay2Story-BenchFID: 66.14 -> 26.71Improved
add masked 3D self-attention (ablation)Lay2Story · Lay2Story-BenchRecall@1: 0.3274 -> 0.7012Improved
inject layout conditions (subject positions and captions) at inferenceLay2Story · Lay2Story-BenchFID: 35.82 -> 26.71Improved
inject layout conditions at inferenceLay2Story · Lay2Story-BenchDreamSim: 0.1602 -> 0.1324Improved
inject layout conditions at inferenceLay2Story · Lay2Story-BenchRecall@1: 0.6376 -> 0.7012Improved
inject layout conditions at inferenceLay2Story · Lay2Story-Benchinference time (s): 13.63 -> 14.02Hurt
replace FLUX.1-dev IP-Adapter with Lay2Story w/o layoutLay2Story w/o lc · Lay2Story-Benchinference time (s): 61.38 -> 13.63Improved
replace FLUX.1-dev IP-Adapter with Lay2Story w/o layoutLay2Story w/o lc · Lay2Story-BenchFID: 33.18 -> 35.82Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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