Wan 2.6 Reference-to-Video Flash for fast reference-guided video generation with optional audio. Supports image/video references (up to 5 total), 720p/1080p, 5-10 second clips with single or multi-shot motion.
Added Feb 4, 2026
Approx. Price
$0.225 per video
Model Type
image-to-video
Settings
Generation controls available for this model.
Output Format
Default Duration
5
2 duration options
Duration
Default
5
Options (2)
5 seconds, 10 seconds
5 or 10 seconds
Generate Audio
Default
Yes
Enable audio output
Orientation
Default
landscape
Options (2)
Landscape, Portrait
Output orientation
Prompt Expansion
Default
false
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
Benchmarks
Benchmarks
No benchmark data is available yet for this model.
Examples
Loading examples…
Related video models
Compare Wan 2.6 Reference-to-Video Flash with similar models from the same provider or model family.
Wan 2.6 Flash
wan-wavespeed-26-flashWan 2.6 Flash for fast image-to-video generation with optional audio. 720p/1080p, 2-15 second clips with single or multi-shot motion.
Wan 2.2 Animate 2
wan-22-animate-2Next-generation character motion transfer with strong identity preservation and prompt-controlled backgrounds. Requires a reference image and driver video; supports 480p/720p up to 120s.
Wan 2.5 Extend Fast
wan-25-extend-fastFast video extension with synchronized audio. Extends a source clip to 3–10 seconds at 720p or 1080p.
Wan 2.5 Fast
wan-25-fastFast text-to-video generation with synchronized audio and optional custom audio. Supports 720p/1080p and 5s or 10s clips.
Wan 2.7 Video
wan-2.7-videoUnified Wan 2.7 video model. One model id that supports text-to-video, image-to-video, reference-to-video, or video editing based on what you upload.
Wan 2.2 Spicy
wan-22-spicyWan 2.2 Spicy image-to-video for fast cinematic animation from a single image. Supports 480p or 720p output with 5 or 8 second clips.