AI Paper Atlas

Research map / Video / Video generation

P-Flow: Prompting Visual Effects Generation

Rui Zhao, Mike Zheng Shou

CVPR 2026 · Video › Video generation · approach: World-model video generation · 1 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 noise prior enhancement to P-Flow (ablation)P-Flow (Wan 2.1 14B) · Open-VFX overallFVD: 1205.47 -> 1072.10Improved
add visual context of previous generated video (ablation)P-Flow (Wan 2.1 14B) · Open-VFX overallFVD: 1072.10 -> 953.10Improved
add logic context (full history of prompts and analyses) (ablation)P-Flow (Wan 2.1 14B) · Open-VFX overallFVD: 953.10 -> 882.63Improved
add logic context (ablation)P-Flow (Wan 2.1 14B) · Open-VFX overallDynamic Degree: 0.81 -> 0.91Improved
add SVD projection of inverted noise (ablation)P-Flow noise prior · Open-VFX image-to-videoFVD: 1052.80 -> 784.51Improved
blend inverted motion noise with random noise (alpha 0.001 vs random only) (ablation)P-Flow noise prior · Open-VFX image-to-videoDynamic Degree: 0.73 -> 0.94Improved
increase blending alpha from 0.001 to 0.01 (ablation)P-Flow noise prior · Open-VFX image-to-videoFID-VID / Dynamic Degree: FID-VID 29.32 -> 29.21; Dyn. Degree 0.94 -> 0.88Mixed
prompt optimization alone without any module vs Wan 2.1 (ablation)P-Flow · Open-VFX overallDynamic Degree: 0.31 -> 0.63Improved
replace one-shot human prompt revision with VLM test-time prompt optimizationWan 2.1 (T2V) · Open-VFX text-to-videoFVD: 1632.10 -> 980.75Improved
human feedback prompt revision on baselineWan 2.1 · Open-VFX overallFID-VID: 38.47 -> 75.33Hurt
P-Flow training-free vs training-based VFX CreatorOpen-VFX image-to-video · Open-VFX image-to-videoDynamic Degree: 0.63 -> 0.94Improved
P-Flow vs VFX Creator on FVDOpen-VFX image-to-video · Open-VFX image-to-videoFVD: 752.95 -> 784.51Hurt

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