Video generation begins in text space by authoring a cinematic screenplay, then materializes into pixels. As contemporary video generators scale to 30 seconds and faithfully follow complex conditions, the textual prompt largely directs the production, planning how actions, camera trajectories, lighting, and sound unfold across multi-shot sequences. In this paper, we present WanPE, a 397B-parameter prompt enhancement model trained on 1.05M real-world videos to master director-level cinematic planning. WanPE formulates shot-level cinematic plans via video-grounded reverse construction and employs Semantic-Consistency GRPO (SC-GRPO) to faithfully preserve user requirements across shots and over time. To benchmark this capability, we curate WanPEval, a human-annotated testbed covering durations from 5 to 30 seconds across varying intent granularities, supported by approximately 11K blind pairwise assessments. When powering Wan3.0's video generator, WanPE-397B boosts human preference over raw user prompts by 10.66-18.84 points at 5-15 seconds and by a dramatic 50.86 points in the 30-second arena. Ablation studies show that reverse construction demonstrates clear superiority over forward rewriting, while SC-GRPO robustly preserves semantic fidelity across model scales. Ultimately, WanPE leads all evaluated commercial offerings at 5-15 seconds and remains competitive with Seedance 2.5 at 30 seconds.
Figures & tables
Figure 1 : Left: Earlier models use optional prompt expansions, while modern video generators can process longer contexts and follow complex instructions. Right: t-SNE shows WanPE outputs align closely with video-grounded captions, while forward-based enhancement exhibits a distribution gap.
Figure 2 : WanPE training pipeline. Video-grounded reverse SFT and semantic-consistency GRPO.
5 seconds
10 seconds
15 seconds
Overall
Method
S
BT
S
BT
S
BT
S
BT
LTX-2.5
18.69
31.23
18.47
34.74
16.10
32.20
17.30
33.02
Kling 3.0
31.11
43.02
23.47
39.84
16.10
34.07
20.80
37.40
HappyHorse 1.1
20.28
32.82
24.00
40.72
26.80
42.39
24.89
40.46
MiniMax-H3
29.09
41.24
36.46
49.59
38.30
51.13
36.40
49.27
Seedance 2.0
46.20
54.20
41.40
52.16
44.31
56.90
43.42
54.70
Table 1 : Expert preference score and Bradley–Terry score on the 5 – 15 seconds subset of WanPEval.
Method
Action
Anim.
Speech
Ad.
Sing & Dance
Drama
Know.
Overall
Exp1: 30-second subset
Seedance 2.5
68.18
46.43
55.00
81.25
60.00
56.00
60.71
59.76
downstream generator: Wan3.0’s video generator
Original request
4.17
9.38
15.79
5.00
22.50
4.00
3.57
9.38
+WanPE-397B
50.00
81.25
73.68
75.00
47.50
53.85
57.14
60.24
Exp2: Reverse vs. forward enhancement
Table 2 : Preference scores S on WanPEval. (i) 30-second subset against Seedance 2.5, under Wan3.0. (ii) Reverse-constructed vs. forward-based enhancement, under Wan3.0. (iii) Format-adapted WanPE vs. native enhancers on LTX-2.5 and MiniMax-H3 in two separate battles.
(i) Semantic consistency
Method
Overall ↑
5 seconds ↑
10 seconds ↑
15 seconds ↑
30 seconds ↑
Perfect ↑
Failure ↓
Fwd. Rewriting
90.7
93.5
91.8
90.3
89.4
55.0
10.0
LTX-2.5-PE
77.3
76.1
81.6
74.9
77.0
33.7
38.6
H3-Context-IR
88.3†
89.4
88.8
87.6
–
54.2†
17.3†
Ours
WanPE-4B-SFT
66.5
67.0
68.4
66.7
64.2
20.1
56.6
Table 3 : (i) Semantic consistency evaluated by gemini-3.1-pro-preview. † denotes results computed on the 5–15-second subset. (ii) Expert preference S for 397B SFT vs. WanPE-397B under Wan3.0.