Aller au contenu
AlibabaVérification

Wan 2.7 / Image to Video

wan-2-7-image-to-video

image vers vidéoSortie: VidéoEntrée: texte + image + audio
Chargement du prix…
Prix catalogue officiel · Non vérifié

Ce qu’il fait

Generate video from a reference image with optional audio.

2–15 seconds · 720p or 1080p

Paramètres d’entrée

Uniquement les champs acceptés par ce modèle. Les champs obligatoires doivent être fournis.

ChampTypeObligatoirePar défautValeurs autorisées et contraintes
prompt
stringfacultatif—

1–5000 chars

firstImageUrl
stringobligatoire—

Choose one of two: 1. first_frame=the first frame of the generated video. 2. first_frame+last_frame=start and end frames generate the video.

HTTPS image URL or media:<uuid>

lastImageUrl
stringfacultatif—

Choose one of two: 1. first_frame=the first frame of the generated video. 2. first_frame+last_frame=start and end frames generate the video.

HTTPS image URL or media:<uuid>

audioUrl
stringfacultatif—

audioUrl MP3 or WAV; maximum 15 MB.

HTTPS audio URL or media:<uuid>

negativePrompt
stringfacultatif—

0–500 chars

resolution
stringobligatoire"720P"

Parmi: "720P", "1080P"

duration
stringobligatoire"5"

Parmi: "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15"

promptExtend
booleanfacultatiftrue

Whether to enable prompt intelligent rewriting. After activation, use the large model to intelligently rewrite the input prompt. For shorter prompt generation, the effect is significantly improved, but it will increase the time consumption.

seed
integerfacultatif—

Randomly select seeds with a value range of [0, 2147483647]. If not specified, the system will automatically generate random seeds. If you need to improve the reproducibility of the generated results, it is recommended to fix the seed value. Please note that due to the probabilistic nature of model generation, even with the same seed, it cannot be guaranteed that the results generated each time will be completely consistent

0–2147483647

Limites et comportement

  • Asynchrone uniquement : soumettez une tâche, puis interrogez le résultat.
  • prompt: 1–5000 chars
  • negativePrompt: 0–500 chars
  • seed: 0–2147483647
  • Les entrées média acceptent des URL HTTPS publiques ou des références media:<uuid> issues de POST /api/v1/media.