Private AI
WanXiang 2.6 - cinematic text-to-video, image-to-video, and reference-to-video generation with multi-shot storytelling support. 720p/1080p, 5-15s clips.
Added Dec 16, 2025
Approx. Price
$0.450 per video
Model Type
both
Generation controls available for this model.
Output Format
Default Duration
5
3 duration options
Duration
Default
5
Options (3)
5 seconds, 10 seconds, 15 seconds
Clip length (R2V supports 5s/10s only)
Orientation (T2V only)
Default
landscape
Options (2)
Landscape, Portrait
Used for text-to-video only
Prompt Expansion
Default
true
Options (2)
true, false
Use AI to expand your prompt
Resolution
Default
720p
Options (2)
720p, 1080p
Output resolution
Shot Type
Default
single
Options (2)
Single, Multi-shot
Single continuous shot or multi-shot sequence
Human preference benchmarks sourced from Artificial Analysis.
Text to Video
#30 / 81
ELO
1191.0
Appearances
3,077
95% CI
-9/9
Image to Video
#42 / 74
ELO
1209.0
Appearances
3,484
95% CI
-10/10
Release Date 2025-12 · Matched as Wan 2.6
Artificial Analysis APILoading examples…