AI Paper Atlas

Research map / Video / Video generation

DreamStyle: A Unified Framework for Video Stylization

Mengtian Li, Jinshu Chen, Songtao Zhao, Wanquan Feng, Pengqi Tu, Qian He

CVPR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion · 6 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 token-specific LoRA (ablation)DreamStyle · Style-image-guided stylizationCSD score: 0.413 -> 0.515Improved
add token-specific LoRA (ablation)DreamStyle · Style-image-guided stylizationDINO score: 0.518 -> 0.526Improved
add SFT stage after CT training (ablation)DreamStyle · Style-image-guided stylizationCSD score: 0.459 -> 0.515Improved
add CT stage before SFT training (ablation)DreamStyle · Style-image-guided stylizationDINO score: 0.483 -> 0.526Improved
add CT stage before SFT training (ablation)DreamStyle · Style-image-guided stylizationCSD score: 0.535 -> 0.515Hurt
add SFT stage after CT training (ablation)DreamStyle · Style-image-guided stylizationDINO score: 0.547 -> 0.526Hurt
use DreamStyle instead of StyleMasterstyle-image-guided stylization · Style-image-guided (T2V)CSD score: 0.198 -> 0.532Improved
use DreamStyle instead of Runway for text-guidedtext-guided stylization · Text-guidedDINO score: 0.504 -> 0.584Improved
use DreamStyle instead of Pixverse on image qualitytext-guided stylization · Text-guidedImage quality: 0.746 -> 0.738Hurt
use DreamStyle instead of VACE for structure preservationfirst-frame-guided stylization · First-frame-guidedDINO score: 0.716 -> 0.640Hurt
use DreamStyle instead of VideoX-Fun for style consistencyfirst-frame-guided stylization · First-frame-guidedCSD score: 0.766 -> 0.851Improved
drop video condition (T2V mode) from DreamStyleDreamStyle · Style-image-guidedCSD score: 0.515 -> 0.532Improved

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