← Saturday, September 26, 2026Models & trainingPaper

WanPE improves long-form video prompts with shot-level cinematic plans

huggingface.co Editor score 8/10

The 397B model uses plans built from 1.05M videos and improves human preference by 10.66–18.84 points at 5–15 seconds and 50.86 points at 30 seconds. It is a substantial example of how prompt planning can improve a generative model’s output.

What

WanPE is a 397B-parameter prompt-enhancement model trained on 1.05M real-world videos to create shot-level cinematic plans.

Method

It uses video-grounded reverse construction and Semantic-Consistency GRPO to preserve user requirements across shots and over time.

Why it matters

With Wan3.0, it raised human preference over raw prompts by 10.66–18.84 points at 5–15 seconds and 50.86 points at 30 seconds.

Read on huggingface.co →

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.