AI Paper Atlas

Research map / Video / Video generation

VACE: All-in-One Video Creation and Editing

Zeyinzi Jiang, Zhen Han, Chaojie Mao, Jingfeng Zhang, Yulin Pan, Yu Liu

ICCV 2025 · Video › Video generation · approach: Autoregressive long video generation · 343 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 Context Adapter tuning (Res-Tuning) instead of full fine-tuning (ablation)VACE · VACE-Benchmark (LTX-Video based, validation loss)training loss convergenceImproved
distribute context blocks evenly instead of continuous shallow blocks (ablation)VACE Context Adapter · VACE-Benchmark (LTX-Video based, validation loss)validation lossImproved
increase number of context blocks (1/4, 1/2, all) (ablation)VACE Context Adapter · VACE-Benchmark (LTX-Video based, validation loss)validation lossImproved
add Concept Decouple module (ablation)VACE · VACE-Benchmark (LTX-Video based, validation loss)validation lossImproved
unified model vs task-specific open-source methods on I2V, inpainting, outpainting, depth, pose, optical flowVACE · VACE-BenchmarkVBench eight indicatorsImproved
small LTX-based VACE vs commercial models on reference-to-videoVACE · VACE-Benchmark R2VVBench indicatorsMixed

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