AI Paper Atlas

Research map / Video / Video generation

Free2Guide: Training-Free Text-to-Video Alignment using Image LVLM

Jaemin Kim, Bryan Sangwoo Kim, Jong Chul Ye

ICCV 2025 · Video › Video generation · approach: Compositional text-to-video diffusion · 5 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 GPT-4o image LVLM guidanceLaVie · VBench text alignment (LaVie)Avg. score: 0.3722 -> 0.3827Improved
add GPT-4o image LVLM guidanceVideoCrafter2 · VBench text alignment (VideoCrafter2)Avg. score: 0.4129 -> 0.4425Improved
ensemble GPT-4o with CLIP rewardLaVie + CLIP · VBench text alignment (LaVie)Avg. score: 0.3780 -> 0.3868Improved
ensemble GPT-4o with ImageRewardVideoCrafter2 + ImageReward · VBench text alignment (VideoCrafter2)Avg. score: 0.4435 -> 0.4483Improved
use weighted sum ensemble rather than consensus (ablation)LaVie + CLIP + GPT · VBench ensemble methods (LaVie + CLIP)Avg. score: 0.5679 -> 0.5738Improved
use weighted sum ensemble rather than normalized sum (ablation)LaVie + CLIP + GPT · VBench ensemble methods (LaVie + CLIP)Avg. score: 0.5734 -> 0.5738No clear effect
use 1-9 scale scoring instead of yes/no logits (ablation)VideoCrafter2 + GPT · VBench text alignment (VideoCrafter2)Avg. score: 0.4358 -> 0.4425Improved
increase samples per step from 5 to 10 (ablation)LaVie + CLIP · VBench text alignment (LaVie)Avg. score: 0.3780 -> 0.3705Hurt
extend guidance range to t in [T,T-10] (ablation)LaVie + CLIP · VBench text alignment (LaVie)Avg. score: 0.3780 -> 0.3635Hurt
add GPT-4o guidance on general video qualityVideoCrafter2 · VBench general video quality (VideoCrafter2)Avg. score: 0.7617 -> 0.7537Hurt
ensemble GPT-4o with ImageReward on general qualityLaVie + IR · VBench general video quality (LaVie)Avg. score: 0.7666 -> 0.7699Improved
use open-source Qwen2.5-VL 3B image LVLM instead of GPT-4o (ablation)LaVie · VBench text alignment (LaVie)Avg. score: 0.3722 -> 0.3816Improved

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