Home/Wan 2.7 Reference-to-Video

Wan 2.7 Reference-to-Video

Video

Wan 2.7 Reference-to-Video model with multimodal input support (text/image/video). Can generate single-character performance or multi-character interaction videos using reference characters. Supports intelligent multi-shot generation. 720P and 1080P resolutions, duration 2~10 seconds, billed per second. Output includes audio by default.

media*

prompt*

0 / 2000

audio

duration

size

watermark

seed

Pending

Parameter festlegen und auf „Generieren“ klicken, um Ergebnisse zu erhalten

Anfrage-JSON

{}

API

Aufgabe übermitteln

curl --location --request POST 'https://api.novita.ai/v3/async/wan2.7-r2v' \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}" \
--data-raw '{}'

Abfrageergebnis

curl --location --request GET "https://api.novita.ai/v3/async/task-result?task_id
=${task_id}" \
--header "Authorization: Bearer ${API_KEY}"