← Back to all generators

wan-video/wan-3.0

Wan 3.0 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

Capabilities

adaptive16:94:31:13:49:16Seed

Cost

Community model (estimated from hardware time)

Input Parameters

promptrequiredstring

Text prompt for the generated video.

aspect_ratiostring

Output aspect ratio, or adaptive selection.

Default: "adaptive"
adaptive16:94:31:13:49:16
audioboolean

Include generated audio.

Default: true
durationunknown

Output duration in seconds. Set to null for smart duration, which lets the model pick a length from the prompt and reference media.

Default: 5
enable_prompt_expansionboolean

Enable intelligent prompt rewriting. Disabling it can save roughly 20-60 seconds of latency but is likely to degrade generation quality.

Default: true
enable_safety_checkerboolean

Enable content moderation for input and output. Disabling it requires account authorization; unauthorized requests are always checked.

Default: true
enable_thinkingboolean

Enable enhanced reasoning before generation.

Default: false
resolutionstring

Output video resolution tier.

Default: "1080p"
480p720p1080p
seedunknown
Updated: 11/7/2026