Providers and ModelsAlibaba Cloud

Wan-2.7

Wan-2.7

Provider: Alibaba Cloud
Category: Video Generation
Endpoint: POST /v1/videos/generations
Context window: —
Served from: Singapore

Multimodal video model supporting T2V, I2V, video editing, and reference-to-video, with high-fidelity output from text, image, or video inputs.

At a glance

FieldValue
Model idwan-2-7
Input modalitiestext
Output modalitiesvideo
Context window—
RegionSingapore
Featuresaudio_sync, character_consistency, multi_shot
NewNo
Native inferenceNo

Pricing

ChargeSpecRate
All Modes 720Pper second$0.10
All Modes 1080Pper second$0.150

Example request

$curl https://api.empiriolabs.ai/v1/videos/generations \
>  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>  -H 'Content-Type: application/json' \
>  -d '{"model": "wan-2-7", "prompt": "sunrise over the ocean", "duration": 6}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyes—Scene description.
modeenumno"t2v"t2v: text-to-video. i2v: animate the attached image. videoedit: edit the attached video. r2v: reference-to-video. · Allowed: t2v, i2v, videoedit, r2v
resolutionenumno"1080p"Allowed: 720p, 1080p
durationnumberno5Clip length in seconds. · Range: 3 – 10
aspect_ratioenumno—Optional. If omitted, the model picks based on input. · Allowed: 16:9, 9:16, 1:1, 4:3, 3:4
imagestringno—Reference image URL. Required for i2v / r2v / videoedit.
videostringno—Reference video URL. Required for videoedit / r2v.
negative_promptstringno""What to avoid.
seednumberno—Reproducibility seed.
audio_settingenumno"auto"auto: generate native audio. origin: keep audio from the reference video (videoedit/r2v only). · Allowed: auto, origin
prompt_extendbooleannotrueLet DashScope rewrite the prompt for better results.
watermarkbooleannofalseAdd an EmpirioLabs watermark.

Live machine-readable schema is also available at GET https://api.empiriolabs.ai/v1/models/wan-2-7.