AI Paper Atlas

Research map / Video / Video generation

From Prompt to Progression: Taming Video Diffusion Models for Seamless Attribute Transition

Ling Lo, Kelvin C.K. Chan, Wen-Huang Cheng, Ming-Hsuan Yang

ICCV 2025 · Video › Video generation · approach: Efficient video diffusion models · 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
apply transitional-direction guidance with neutral prompt anchoring on VideoCrafter2VideoCrafter2 · CAT-BenchWholistic Transition Score (overall): 0.0022 -> 0.1486Improved
add neutral prompt anchoring (anchor middle frame to a neutral prompt) (ablation)transitional-direction guidance · qualitative example (car, sunny to rainy)visual consistencyImproved
use full descriptive prompts instead of isolated attribute words for the transitional direction (ablation)transitional-direction guidance · qualitative example (hat color)transition precisionImproved
increase scale factor alpha from [0,1] to [0,2] (ablation)transitional-direction guidance · qualitative example (sunny to rainy)transition intensityImproved
increase scale factor alpha to [0,5] (ablation)transitional-direction guidance · qualitative example (sunny to rainy)visual artifactsHurt
reduce sampling steps to 80% (ablation)Ours · Inference timeseconds: 453.71 -> 349.23Improved
apply method to OpenSora backboneOpenSora · CAT-BenchWholistic Transition Score: 0.0035 -> 0.1622Improved
apply method to OpenSora backboneOpenSora · CAT-BenchBackground Consistency: 0.9701 -> 0.9602Hurt
apply method to VideoCrafter2VideoCrafter2 · CAT-Bench video qualityDynamic Degree: 0.4750 -> 0.7083Improved
apply method to VideoCrafter2VideoCrafter2 · CAT-Bench video qualityConsistency: 0.9639 -> 0.9537No clear effect
use prompt interpolation (Gen-L, FreeNoise) for binary beard attributeGen-L / FreeNoise · CAT-Bench beardWholistic Transition Score: Gen-L 0.0015, FreeNoise 0.0003 vs Ours 0.0332Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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