AI Paper Atlas

Research map / Video / Video generation

DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

Jinbo Xing, Menghan Xia, Yong Zhang, Haoxin Chen, Wangbo Yu, Hanyuan Liu, Gongye Liu, Xintao Wang, Ying Shan, Tien-Tsin Wong

ECCV 2024 · Video › Video generation · approach: Efficient video diffusion models · 296 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 context conditioning stream (CLIP full visual tokens) (ablation)DynamiCrafter · MSR-VTTFVD: 372.80 -> 234.66Improved
add visual detail guidance (VDG) image concatenation stream (ablation)DynamiCrafter · MSR-VTTFVD: FVD 159.24 -> 234.66; PIC 0.6945 -> 0.5803Mixed
add adaptive gating lambda in context stream (ablation)DynamiCrafter · MSR-VTTFVD: 241.38 -> 234.66Improved
use full CLIP visual tokens instead of a single global token (ablation)DynamiCrafter · MSR-VTTFVD: 286.84 -> 234.66Improved
fine-tune only spatial layers instead of the entire T2V model (ablation)DynamiCrafter · MSR-VTTFVD: 364.11 -> 234.66Improved
randomly select conditioning frame instead of always the first frame (ablation)DynamiCrafter · MSR-VTTFVD: 309.23 -> 234.66Improved
train context network on SD first (two-stage) instead of directly on T2V (one-stage)DynamiCrafter · training convergenceconvergenceImproved
DynamiCrafter vs I2VGen-XL on UCF-101 KVDDynamiCrafter · UCF-101KVD: 58.59 -> 62.47Hurt

Later papers that compared with this method

31 later accepted papers report DynamiCrafter as a baseline in their results tables; 28 of them report a better number on most of the results they share with it.

23 more not listed.

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