infery
← All models

Wan 3.0

wan-3.0-reference-to-video

Video generationby Alibaba

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

Example

Details

Accepts
text + audio + image + video

Pricing

Price
0.021 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seed
audiobooleanInclude generated audio.
promptText prompt directing how the reference media is used. Reference media can be addressed positionally, e.g. 'the subject in Image 1 walks past Video 1'.
web_urlPublic webpage URL to base the video on. Requires enable_thinking=true. Only pages that do not require login can be read.
durationOutput duration in seconds. Set to null for smart duration, which lets the model pick a length from the prompt and reference media.
file_urlDocument URL to base the video on. Requires enable_thinking=true.
resolutionstringenum: 480p, 720p, 1080pOutput video resolution tier.
aspect_ratiostringenum: adaptive, 16:9, 4:3, 1:1, 3:4, 9:16Output aspect ratio, or adaptive selection.
enable_thinkingbooleanEnable enhanced reasoning before generation.
reference_audio_urlsarrayUp to 5 reference audio URLs totaling at most 15 seconds.
reference_image_urlsarrayUp to 10 reference image URLs.
reference_video_urlsarrayUp to 5 reference video URLs totaling at most 15 seconds. Each clip must be at least 16 fps.
enable_safety_checkerbooleanEnable content moderation for input and output. Disabling it requires account authorization; unauthorized requests are always checked.
enable_prompt_expansionbooleanEnable intelligent prompt rewriting. Disabling it can save roughly 20-60 seconds of latency but is likely to degrade generation quality.

Output

FieldTypeDescription
seedintegerThe seed used for generation.
videoThe generated video file.
durationnumberGenerated video duration in seconds.
actual_prompt