AI Paper Atlas

Research map / Video / Video generation

Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM

Yatai Ji, Jiacheng Zhang, Jie Wu, Shilong Zhang, Shoufa Chen, Chongjian Ge, Peize Sun, Weifeng Chen, Wenqi Shao, Xuefeng Xiao, Weilin Huang, Ping Luo

ICCV 2025 · Video › Video generation · approach: Compositional text-to-video diffusion · 19 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 DPO preference alignment after SFT (ablation)Prompt-A-Video (CogVideoX) · WebVid in-domainVideoScore VQ: 2.770 -> 2.900Improved
add DPO preference alignment after SFT (ablation)Prompt-A-Video (Open-Sora 1.2) · WebVid in-domainVideoScore VQ: 3.029 -> 3.090Improved
add a second DPO iteration (ablation)Prompt-A-Video (Open-Sora 1.2) · WebVid in-domainVideoScore VQ: 3.090 -> 3.254Improved
add a third DPO iteration (ablation)Prompt-A-Video (CogVideoX) · WebVid in-domainVideoScore DD: 3.183 -> 3.156Hurt
add a third DPO iteration (ablation)Prompt-A-Video (Open-Sora 1.2) · WebVid in-domainVideoScore DD: 3.411 -> 3.214Hurt
add VideoScore video-level reward to image-level rewards (ablation)Prompt-A-Video DPO · VBench 100-prompt subsetVideoScore VQ: 2.660 -> 2.679Improved
add MPS reward (ablation)Prompt-A-Video DPO · VBench 100-prompt subsetVBench image quality: 0.653 -> 0.662Improved
add Aesthetic Predictor reward (ablation)Prompt-A-Video DPO · VBench 100-prompt subsetVBench aesthetic quality: 0.614 -> 0.627Improved
add DPO on top of SFT for text-to-image (ablation)Prompt-A-Video · HPSv2 averageHPS score: 26.81 -> 27.09Improved
use text-to-image prompt booster Promptist for video promptsPromptist · WebVid in-domain (CogVideoX)VideoScore average: 2.989 -> 2.873Hurt
replace GLM-4 refinement with Prompt-A-VideoPrompt-A-Video · VBench (CogVideoX)dynamic degree: 56.94 -> 65.28Improved
replace GPT-4o refinement with Prompt-A-VideoPrompt-A-Video · WebVid in-domain (Open-Sora 1.2)VideoScore average: 3.079 -> 3.318Improved

Later papers that compared with this method

2 later accepted papers report Prompt-A-Video as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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